The life of a prescription at Amazon Pharmacy

From pricing estimation and regulatory compliance to inventory management and chatbot assistants, machine learning models help Amazon Pharmacy customers stay healthy and save time and money.

Pharmacies play a vital role in ensuring patients’ health, but the process of dispensing medications is far more complex than it may appear. At Amazon Pharmacy, we are using artificial intelligence (AI) and cutting-edge technologies to remove this complexity and improve patients’ experiences.

The pharmacy challenge

When a prescription arrives at a pharmacy, its details must be entered into the pharmacy's software system. Then, a licensed pharmacist reviews the prescription to verify the patient's information, check for potential drug interactions or allergies, and confirm that the prescribed medication, dosage, and instructions are appropriate and accurate.

This process is susceptible to errors — even if the prescription arrives electronically. A U.S. study estimated that there are approximately 51.5 million dispensing errors annually in community pharmacies, with a meta-analysis supporting an error rate of around 1.5%.

Related content
Amazon Health Services' Sunita Mishra and Columbia University’s Katrina Armstrong discuss technology's potential role in medical settings.

Pharmacies must also handle billing and insurance claims for their patients. These are involved calculations based on patients’ specific insurance policies, their copay responsibilities, and the rates that the pharmacy has negotiated with different insurance providers. In fact, just identifying a patient's insurance can be challenging. The result is that patients often do not know the prices they will pay for their medications until the end of the process, when they’re picking up their prescriptions at a retail pharmacy or checking out online.

After a prescription has been validated and the purchase completed, the pharmacy staff must locate the specific medication in their inventory. However, it's possible that at this stage, the prescribed medication, the required strength, or the preferred brand may no longer be available. Providing a substitute could necessitate contacting the prescribing physician again for approval. Additionally, depending on the substitution, the billing and insurance process may need to be re-initiated to account for any changes in pricing or coverage.

Once the medication is ready for dispensing, the pharmacist provides the patient with detailed instructions on how to properly take it. Patients may also have questions regarding their insurance coverage or costs. However, these conversations often take place in public areas, which can be uncomfortable for patients who have personal or sensitive questions.

Finally, patients need convenient access to pharmacists at any time, day or night. This allows patients to report how they are feeling while taking their medications, which can help pharmacists provide better guidance and support throughout the treatment process.

The AI-powered pharmacy

Amazon Pharmacy uses large language models (LLMs) to enhance the accuracy, safety, and speed of prescription processing. First, we use LLMs to transcribe raw prescription data into structured, standardized formats that are seamlessly processed by software and more easily understood by patients. For example, medical abbreviations like "PRN" and "QID" are transformed into their full-text equivalents, such as "take as needed" and "take four times a day," respectively.

After standardizing the prescription data, the system performs a validation step that includes checking the medication names, dosage forms, strengths, and directions for use against an industry database. After validation, all prescriptions are still carefully reviewed and verified by licensed pharmacists. By leveraging this automated process, Amazon Pharmacy has reduced the number of near-miss events (potential medication errors) by 50% and improved processing speed by up to 90%. This allows our pharmacists to focus their time and attention on critical tasks, such as providing personalized care and addressing complex medication-related issues.

Pharmacy.png
The AI workflow at Amazon Pharmacy.

Amazon Pharmacy understands the importance of price transparency for customers. When a patient is using insurance to cover the cost of medication, Amazon Pharmacy will first try to obtain the exact price directly from the insurance provider. However, if this real-time pricing information is not available, Amazon Pharmacy will provide an estimated out-of-pocket cost for the patient's copay, without requiring the customer to go through the entire checkout process first.

To generate accurate price estimates, Amazon Pharmacy uses an ensemble of decision-tree-based models. These models take into account factors such as historical claims data (time series features) and static information such as the specific medication, the number-of-days' supply, and the quantity prescribed. By providing upfront pricing information, either the exact cost or a reliable estimate, Amazon Pharmacy aims to increase transparency and help patients understand their out-of-pocket expenses before committing to purchases. Additionally, Amazon Pharmacy searches for applicable industry coupons and automatically applies them to orders. We also use ML to validate the patient's insurance registration and claim requests to insurance providers.

Amazon is known for its extensive logistics and fulfillment capabilities, and Amazon Pharmacy takes advantage of Amazon's vast network of same-day and local delivery facilities, as well as innovative transportation methods like Prime Air drones. Additionally, Amazon Pharmacy employs specialized automation technologies, such as robotic vial-filling systems, to streamline the medication-dispensing process, enabling prompt delivery of medications to patients across the nation.

Beyond the physical logistics infrastructure, Amazon Pharmacy has developed its own order fulfillment system to handle complex medication-routing and -dispensing logic, while ensuring compliance with over 160 different pharmacy regulatory bodies across the United States. For example, if a medication for an order is no longer available at the closest fulfillment center, Amazon Pharmacy can identify the next best eligible facility to fulfill the order, even if it's in a different state, provided that the relevant state regulations allow for such cross-state fulfillment.

Related content
ARA recipient Marinka Zitnik is focused on how machine learning can enable accurate diagnoses and the development of new treatments and therapies.

Moreover, Amazon Pharmacy's order fulfillment algorithm takes into account regional variations in insurance eligibility. In such cases, Amazon Pharmacy will first validate that there are no changes to the patient's copay. If changes are required, Amazon Pharmacy will work with the insurance providers to clarify the benefits. To accomplish all of this, Amazon Pharmacy's order fulfillment solution employs a combination of operations research techniques, such as optimization solvers, and deep-learning models such as variational autoencoders and diffusion models. These models help simulate different scenarios and optimize the fulfillment process to ensure efficient and compliant delivery of medications to patients.

Amazon Pharmacy also introduced personalized AI-powered chatbots to assist users. These virtual assistants can answer frequently asked questions about Amazon Pharmacy, such as how to enroll in the service. In a first for the industry, Amazon Pharmacy's chatbot also provides personalized support, allowing patients to ask questions about their medication orders, delivery status, prescription transfers, and inventory availability. If a patient prefers, there is always 24/7 access to direct pharmacist support and the customer care team.

Implementing a personalized AI chatbot in the healthcare setting is a complex task. It's crucial to safeguard patients' privacy and ensure the highest level of accuracy, avoiding LLM hallucinations. To address these challenges, Amazon Pharmacy has enhanced the typical retrieval-augmented generation (RAG) approach used for LLM chatbots. The enhancements include input and output guardrails, the use of ensembles of specialized (mini) AI models, and a continuous model improvement process through reinforcement learning using human feedback (RLHF).

The digital pharmacy counter

Amazon Pharmacy is leveraging ML and optimization algorithms to streamline the complex process of dispensing medications. By addressing long-standing challenges such as data entry errors, lack of price transparency, intelligent nationwide medication fulfillment, and personalized-AI-based experiences, Amazon Pharmacy enables patients to save time, save money, and stay healthy.

Related content
Gari Clifford, the chair of the Department of Biomedical Informatics at Emory University and an Amazon Research Award recipient, wants to transform healthcare.

For example, it is not uncommon for medications to go into short-term back order (STBO), especially new medications entering the market, as was recently the case with the GLP-1 line of medications used for diabetes and weight loss. Amazon Pharmacy’s intelligent-fulfillment solution has enabled an 85% decrease in delivery estimate misses for unforeseen reasons, including STBOs.

The AI-powered Amazon Pharmacy assistant helps customers navigate the complexities of the pharmacy industry, providing 24/7 assistance on topics like prescription tracking, insurance coverage, medication availability, and cost-saving strategies. Half of the customers who interact with the assistant don't require additional human support, which saves them time and effort. (For customers who still need assistance, Amazon Pharmacy likewise provides 24/7 access to pharmacist support.) Additionally, the assistant provides real-time medication transfer or shipment status updates in response to patient queries, handling follow-up questions to recommend next steps.

For all the success of our AI-based systems, however, Amazon Pharmacy’s research and engineering teams remain hard at work. We will continue pushing the envelope in scaling medication dispensing, improving personalized AI-based chatbots and assistants, and transitioning toward a longitudinal pharmacy that is proactively looking out for patients.

Research areas

Related content

US, TX, Austin
Our team is involved with pre-silicon design verification for custom IP. A critical requirement of the verification flow is the requirement of legal and realistic stimulus of a custom Machine Learning Accelerator Chip. Content creation is built using formal methods that model legal behavior of the design and then solving the problem to create the specific assembly tests. The entire frame work for creating these custom tests is developed using a SMT solver and custom software code to guide the solution space into templated scenarios. This highly visible and innovative role requires the design of this solving framework and collaborating with design verification engineers, hardware architects and designers to ensure that interesting content can be created for the projects needs. Key job responsibilities Develop an understanding for a custom machine learning instruction set architecture. Model correctness of instruction streams using first order logic. Create custom API's to allow control over scheduling and randomness. Deploy algorithms to ensure concurrent code is safely constructed. Create coverage metrics to ensure solution space coverage. Use novel methods like machine learning to automate content creation.
IL, Tel Aviv
We are seeking an Applied Scientist to help build Amazon’s next-generation customer memory and personalization systems. Are you interested in building systems that move beyond reacting to customer behavior, to actually understanding and remembering it over time? Our team is building Amazon’s customer memory layer – a system that extracts, curates, and reasons over customer knowledge to power next-generation personalization. This includes transforming noisy, unstructured signals into durable, high-quality representations of customer preferences, intents, and life events, and using them in real time to improve customer experiences. We are part of Amazon’s Personalization organization, a high-performing group that leverages large-scale machine learning, generative AI, and distributed systems to deliver highly relevant customer experiences. We tackle challenging problems at the intersection of information extraction, knowledge representation, LLM reasoning, and recommendation systems. Our systems operate under real-world constraints of scale, latency, and quality, requiring careful tradeoffs between precision, recall, and responsiveness. This team plays a central role in defining how Amazon understands its customers, and how that understanding is applied across the shopping experience. As an Applied Scientist, you will design and build ML and LLM-powered solutions for Amazon's customer memory and personalization systems. You will work on how customer knowledge is extracted, validated, and applied in production systems. You will own the end-to-end delivery of ML solutions, from problem formulation and modeling to offline and online experimentation, and production deployment at scale. You will deliver high-quality, scalable systems that power customer-facing experiences. You will drive work across areas such as fact extraction, memory quality and lifecycle, temporal reasoning, and grounded personalization, while navigating tradeoffs between quality, latency, and coverage. You will collaborate closely with engineering and product teams to translate research into measurable customer impact. Please visit https://www.amazon.science for more information.
US, NY, New York
The Ads Measurement Science team in the Measurement, Ad Tech, and Data Science (MADS) team of Amazon Ads serves a centralized role developing solutions for a multitude of performance measurement products. We create solutions which measure the comprehensive impact of their ad spend, including sales impacts both online and offline and across timescales, and provide actionable insights that enable our advertisers to optimize their media portfolios. We leverage a host of scientific technologies to accomplish this mission, including Generative AI, classical ML, Causal Inference, Natural Language Processing, and Computer Vision. We are hiring an Economist on the team to develop the next generation of incrementality measurement products, capturing the effect of advertising in driving sales as well as the effects of measurement tools on advertiser engagement with Amazon. As an Economist on the team, you will lead the design, implementation, and validation of large-scale causal inference methodologies to capture these properties. You will communicate your results with science and business leaders, and partner with other scientists and engineers to carry solutions into production. Key job responsibilities Leverage deep expertise in causal inference to develop robust, causally grounded ads measurement solutions Disambiguate problems to propose clear evaluation frameworks and success criteria Work autonomously and write high quality technical documents Partner closely with other scientists to deliver large, multi-faceted technical projects Share and publish works with the broader scientific community through meetings and conferences Communicate clearly to both technical and non-technical audiences and leaders Contribute new ideas that shape the direction of the team's work Mentor more junior scientists and participate in the hiring process
US, NY, New York
The Ads Measurement Science team in the Measurement, Ad Tech, and Data Science (MADS) team of Amazon Ads serves a centralized role developing solutions for a multitude of performance measurement products. We create solutions which measure the comprehensive impact of advertiser's ad spend, including sales impacts both online and offline and across timescales, and provide actionable insights that enable our advertisers to optimize their media portfolios. We also own the science solutions for AI tools that unlock new insights and automate high-effort customer workflows, such as custom query and report generation based on natural language user requests. We leverage a host of scientific technologies to accomplish this mission, including Generative AI, classical ML, Causal Inference, Natural Language Processing, and Computer Vision. As an Applied Scientist on the team, you will lead measurement solutions end-to-end from inception to production. You will propose, design, analyze, and productionize models to provide novel measurement insights to our customers. Key job responsibilities Leverage deep expertise in one or more scientific disciplines to invent solutions to ambiguous ads measurement problems Disambiguate problems to propose clear evaluation frameworks and success criteria Work autonomously and write high quality technical documents Implement a significant portion of critical-path code, and partner with engineers to directly carry solutions into production Partner closely with other scientists to deliver large, multi-faceted technical projects Share and publish works with the broader scientific community through meetings and conferences Communicate clearly to both technical and non-technical audiences Contribute new ideas that shape the direction of the team's work Mentor more junior scientists and participate in the hiring process About the team We are a team of scientists across Applied, Research, Data Science and Economist disciplines. You will work with colleagues with deep expertise in ML, NLP, CV, Gen AI, and Causal Inference with a diverse range of backgrounds. We partner closely with top-notch engineers, product managers, sales leaders, and other scientists with expertise in the ads industry and on building scalable modeling and software solutions.
US, CA, Pasadena
The Amazon Center for Quantum Computing in Pasadena, CA, is looking to hire a Fabrication R&D Scientist with experience in semiconductor process development who will aid in Amazon’s effort to bring cloud quantum computing services to its worldwide customer base. You will join a multi-disciplinary team of scientists, and hardware and software engineers working at the forefront of quantum computing. Through your work inside and outside of the cleanroom environment in the fabrication research and development group, you will solve problems related to developing next-generation quantum processors. Candidates must have a demonstrated background in sound scientific and engineering principles, and must have excellent data analysis, bias for action, problem solving, and communication skills, and be highly motivated and curious to research and learn new technical topics as needed. As a Fab R&D scientist you will be expected to work on new ideas and stay abreast of novel approaches in fabricating and packaging superconducting quantum processors. Working effectively within a team environment is critical. Diverse Experiences Amazon values diverse experiences. Even if you do not meet all the preferred qualifications and skills listed in the job description, we encourage candidates to apply. If your career is just starting, hasn’t followed a traditional path, or includes alternative experiences, don’t let it stop you from applying. Work/Life Balance Our team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives. Mentorship & Career Growth We’re continuously raising our performance bar as we strive to become Earth’s Best Employer. That’s why you’ll find endless knowledge-sharing, mentorship and other career-advancing resources here to help you develop into a better-rounded professional. Export Control Requirement Due to applicable export control laws and regulations, candidates must be either a U.S. citizen or national, U.S. permanent resident (i.e., current Green Card holder), or lawfully admitted into the U.S. as a refugee or granted asylum, or be able to obtain a US export license. If you are unsure if you meet these requirements, please apply and Amazon will review your application for eligibility. Key job responsibilities Responsibilities include developing and optimizing processes to fabricate high-coherence superconducting qubits; developing advanced 3DI interconnect and routing technologies for integrating superconducting quantum technologies; analyzing inline metrology and electrical test data; developing and maintaining integration documentation, design rules, and standard operating procedures; interacting with project leads to provide feedback that continuously improves different processes; staying updated with the latest advancements and industry trends in process integration and apply knowledge to improve processes and drive innovation providing technical guidance and support to junior colleagues, fostering a collaborative and knowledge-sharing work environment. A day in the life The candidate will develop novel technologies using micro-/nano-fabrication techniques inside the cleanroom (independently or in collaboration with other scientists, engineers, and technicians) for next-generation quantum computing. Outside the cleanroom, the candidate will plan experiments, analyze data, and conceive future innovations.
US, WA, Bellevue
The Amazon Middle Mile Science team is seeking an Applied Scientist to be part of a team solving complex airline operations problems to reduce cost and improve performance. You will work closely with product, research science and technical leaders throughout Amazon Air, Amazon Delivery Technology and and will be responsible for influencing funding decisions in areas of investment that you identify as critical future product offerings. You will partner with software developers and data scientists to build end-to-end data pipelines and production code, and you will have exposure to senior leadership as we communicate results and provide scientific guidance to the business. You will analyze large amounts of business data, build the or models that will enable us to continually delight our customers worldwide. The ideal candidate will have extensive experience in Science work, business analytics and have the aptitude to incorporate new approaches and methodologies while dealing with ambiguities. Excellent business and communication skills are a must to develop and define key business questions and build models that answer those questions. You should have a demonstrated ability to think strategically and analytically about business, product, and technical challenges. Further, you must have the ability to build and communicate compelling value propositions, and work across the organization to achieve consensus. This role requires a strong passion for customers, a high level of comfort navigating ambiguity, and a keen sense of ownership and drive to deliver results. Key job responsibilities - Partnership with the engineering and operations to drive modeling and design for complex business problems. - Drive full life-cycle projects. - Design and prototype decision support tools (product) to automate standardized processes and optimize trade-offs across the full decision space. - Execute complex modeling analyses to aid management in making key business decisions and set new policies.
US, CA, San Francisco
We are seeking a Product Manager, Data Strategy & Physical AI to define and execute the long-term product vision for FAR's AI-powered robotics platform. The intersection of foundation models and physical intelligence is creating a once-in-a-generation opportunity to reimagine how intelligent systems perceive, reason, and act in the real world. We need a visionary product leader who can treat data as our primary competitive moat and translate research frontiers into scalable, production-grade capabilities. In this role, you will champion our core data strategy for foundation model creation, building a partner and tool ecosystem to systematically acquire, label, and iteratively improve physical AI datasets. You will architect a continuous data collection flywheel across deployed robot fleets, transforming real-world kinematics, video, and force-torque telemetry from edge operations back into high-fidelity training tokens. Recognizing the limitations of real-world environments, you will also lead the strategy to create high-fidelity synthesized datasets, utilizing advanced physics engines and simulation to generate diverse training tokens at massive scale. Key job responsibilities Data Acquisition & Labeling Ecosystem: Establish the partnerships, tools, and vendor pipelines necessary to acquire, curate, and continuously label multi-modal datasets for training large-scale models. Fleet Data Flywheel Infrastructure: Architect the framework for a continuous data flywheel that securely streams high-frequency kinematics, egocentric video, and force-torque telemetry from real-world robot fleets back into the training loop. Synthetic Data & Simulation Strategy: Define the strategy for generating high-fidelity, physics-aligned synthesized datasets using advanced simulation environments to scale training tokens for edge-case scenarios and long-horizon tasks. Data Compliance & Governance: Partner with operations, privacy, legal, and security teams to build enterprise-grade data management pipelines that programmatically enforce data minimization, anonymization, and CCPA/GDPR compliance. Data Quality & Token Curation: Implement automated telemetry filtering and dataset pruning strategies to identify high-value operational logs, eliminate redundant fleet data, and optimize training compute costs. Cross-Functional Physical AI Delivery: Act as the strategic bridge between machine learning research scientists, simulation developers, robotics engineers, and hardware teams to deliver data-ready platform features that improve physical reliability. About the team At Frontier AI & Robotics, we're not just advancing robotics - we're reimagining it from the ground up. Our team is building the future of intelligent robotics through frontier foundation models and end-to-end learned systems. We tackle some of the most challenging problems in AI and robotics, from developing sophisticated perception systems to creating adaptive manipulation strategies that work in complex, real-world scenarios. What sets us apart is our unique combination of ambitious research vision and practical impact. We leverage Amazon's computational infrastructure and rich real-world datasets to train and deploy state-of-the-art foundation models. Our work spans the full spectrum of robotics intelligence - from multimodal perception using images, videos, and sensor data, to sophisticated manipulation strategies that can handle diverse real-world scenarios. We're building systems that don't just work in the lab, but scale to meet the demands of Amazon's global operations. Join us if you're excited about pushing the boundaries of what's possible in robotics, working with world-class researchers, and seeing your innovations deployed at unprecedented scale.
US, WA, Seattle
Amazon Search is reinventing how customers find products through natural-language and semantic understanding. We are looking for an Applied Scientist II to push the science behind Natural Language Search that interprets complex, constraint-rich shopping queries, retrieves and ranks the most relevant products. You will build and ship large-scale relevance and ranking models that measurably reduce the rate at which customers see irrelevant results, working on problems that span query understanding, semantic matching, and contextual ranking at Amazon scale. Key job responsibilities - Design, train, and ship deep-learning ranking and semantic-matching models that improve search relevance and reduce how often customers see irrelevant results, across hard query types. - Build the training data and evaluation methods that make these models work: synthetic and historical labels, hard-negative mining, and targeted sampling at the cases where search fails. - Develop signals that match product attributes to what the customer actually asked for. - Run offline and online A/B experiments, analyze precision/recall tradeoffs, and iterate to launch. - Work with engineers and scientists across teams to take models from prototype to production at Amazon scale. A day in the life You work alongside scientists and engineers on some of the hardest open problems in search relevance, teaching models to understand what customers really mean when they ask for something specific and nuanced. A typical day blends model development and data curation with sharp experiment analysis: diagnosing where search breaks down for a query segment, designing the fix, and proving the gains through offline metrics and live A/B tests that reach real Amazon customers. The work spans the full range, from surgical fixes that resolve stubborn failure pattern to broad modeling changes that move relevance for millions of queries at once. You'll see your ideas go from whiteboard to production fast, present results regularly to wider team, and help shape the team's relevance roadmap worldwide. About the team We are the science team behind Amazon's semantic search relevance and ranking. We own the models that understand nuanced, multi-constraint shopping queries and show products customers actually want. We operate close to production, measure ourselves on real customer-impact metrics, and run a culture of fast, rigorous experimentation. Every model decision is grounded in data.
US, WA, Seattle
As part of the AWS Applied AI Solutions organization, we're advancing the frontier of trust and safety systems for cloud-based communication services. Our vision is to be the trusted foundation for transforming every business with Amazon AI teammates. Our mission is to deliver turnkey, enterprise-grade foundational AI capabilities that create delightful AI powered solutions. We're building sophisticated AI systems that protect infrastructure from evolving threats while enabling legitimate high-volume users to operate without friction, with messaging services at scale as a key application area. Key job responsibilities - Develop advanced machine learning approaches and agentic systems that autonomously adapt to evolving threat patterns across cloud communication services - Create behavioral detection models that quickly identify malicious patterns after onboarding rather than creating friction during signup - Design intelligent resource allocation algorithms that optimize service delivery based on real-time feedback - Develop frameworks operating at scale across diverse usage patterns, analyzing hundreds of thousands of daily active customers - Research novel approaches combining AI agents with trust and safety systems to solve complex security problems - Collaborate with engineering teams to integrate science components into production systems - Conduct rigorous experimentation and establish evaluation frameworks to measure solution performance A day in the life As an Applied Scientist, you'll develop fraud detection algorithms and AI-powered security systems while maintaining a clear path to customer impact. You'll investigate novel approaches to behavioral analysis, develop methods for real-time reputation assessment, and validate ideas through rigorous experimentation. You'll collaborate with other scientists and engineers to transform research insights into scalable solutions, work directly with enterprise customers to understand requirements, and help shape the future of cloud security technology. About the team Our team is a central science organization supporting multiple product teams across AWS Core Services. We tackle fundamental challenges in AI and machine learning that require novel approaches beyond off-the-shelf solutions. Working at the intersection of machine learning, large language models, and domain-specific applications, we develop practical techniques that advance the state-of-the-art while maintaining a clear path to customer impact. Our team builds deep domain expertise across geospatial intelligence, trust and safety systems, autonomous operations, and other critical areas, collaborating closely with engineering teams to transform research insights into scalable production solutions.
IN, KA, Bengaluru
Alexa International is looking for passionate, talented, and inventive Senior Applied Scientists to help build industry-leading technology with Large Language Models (LLMs) and multimodal systems, requiring strong deep learning and generative models knowledge. Senior applied scientists will drive cross-team scientific strategy, influence partner teams, and deliver solutions that have broad impact across Alexa's international products and services. Key job responsibilities As a Applied Scientist II with the Alexa International team, you will work with talented peers to develop novel algorithms and modeling techniques to advance the state of the art with LLMs, particularly delivering industry-leading scientific research and applied AI for multi-lingual applications — a challenging area for the industry globally. Your work will directly impact our global customers in the form of products and services that support Alexa+. You will leverage Amazon's heterogeneous data sources and large-scale computing resources to accelerate advances in text, speech, and vision domains. The ideal candidate possesses a solid understanding of machine learning, speech and/or natural language processing, modern LLM architectures, LLM evaluation & tooling, and a passion for pushing boundaries in this vast and quickly evolving field. They thrive in fast-paced environment, like to tackle complex challenges, excel at swiftly delivering impactful solutions while iterating based on user feedback, and are able to influence and align multiple teams around a shared scientific vision. A day in the life * Analyze, understand, and model customer behavior and the customer experience based on large-scale data. * Build novel online & offline evaluation metrics and methodologies for multimodal personal digital assistants. * Fine-tune/post-train LLMs using advanced and innovative techniques like SFT, DPO, Reinforcement Learning (RLHF and RLAIF) for supporting model performance specific to a customer’s location and language. * Quickly experiment and set up experimentation framework for agile model and data analysis or A/B testing. * Contribute through industry-first research to drive innovation forward. * Drive cross-team scientific strategy and influence partner teams on LLM evaluation frameworks, post-training methodologies, and best practices for international speech and language systems. * Lead end-to-end delivery of scientifically complex solutions from research to production, including reusable science components and services that resolve architecture deficiencies across teams. * Serve as a scientific thought leader, communicating solutions clearly to partners, stakeholders, and senior leadership. * Actively mentor junior scientists and contribute to the broader internal and external scientific community through publications and community engagement.