Applied Scientist, Agentic Automated Reasoning Group

Amazon • Seattle, WA

1d • Onsite

About The Position

The Agentic Automated Reasoning Group is pioneering the next generation of neuro-symbolic tools, fusing breakthroughs in artificial intelligence with the scale of the cloud and deep expertise in automated reasoning. This role is within the Automated Reasoning checks team, seeking an Applied Scientist experienced in building scalable formal reasoning solutions. The team is building the next generation of tools and services by combining Automated Reasoning, GenAI, and Agentic AI at cloud computing scale. The scientist will propose solutions, create software prototypes, and move them into production systems using modern software development tools and methodologies, supporting and scaling these solutions to meet customer demand. Strong verbal and written communication skills are essential for delivering high-quality results in a fast-paced environment. AWS uses automated reasoning technology and mathematical proofs to provide customers with answers about security, availability, durability, and functional correctness, referred to as provable security.

As an Applied Scientist in the Agentic Automated Reasoning Group, you will play a pivotal role in shaping product features from beginning to end. You will define and implement new automated reasoning features using scalable and efficient approaches, apply software engineering best practices, work in an agile, startup-like development environment, deliver high-quality scientific artifacts, and help drive business decisions.

Requirements

• PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
• Experience in patents or publications at top-tier peer-reviewed conferences or journals
• Experience programming in Java, C++, Python or related language
• Experience in investigating, designing, prototyping, and delivering new and innovative system solutions

Nice To Haves

• Experience using Unix/Linux
• Experience in professional software development

Responsibilities

• Design and implement scalable, production-grade neuro-symbolic systems that integrate formal reasoning with GenAI to deliver reliable, verifiable outcomes for AWS customers.
• Design and run reinforcement learning pipelines (GRPO, PPO, DPO) to optimize language models for formal reasoning and autoformalization tasks.
• Design and run experiments to measure model quality, latency, and cost tradeoffs across model sizes and training strategies.
• Collaborate cross-functionally with product, engineering, and science teams as well as external customers to deeply understand pain points, gather requirements, and translate them into neuro-symbolic features that solve real-world problems.
• Enhance and extend the capabilities of formal reasoning systems to meet the demands of GenAI and agentic applications — including areas such as hallucination detection, policy verification, and automated guardrails.
• Own the end-to-end science lifecycle — from research and experimentation through production deployment — defining metrics to measure system performance and the real-world impact of neuro-symbolic solutions.
• Advance the state of the art through publications at top-tier venues, patents, or open-source contributions, strengthening Amazon's position as a leader in automated reasoning and neuro-symbolic AI.

Benefits

• health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage)
• 401(k) matching
• paid time off
• parental leave

What This Job Offers

• Job Type: Full-time
• Career Level: Senior