Senior Applied Scientist, Agentic Automated Reasoning Group

Description

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 our deep expertise in automated reasoning. If you're driven to push the boundaries of what's possible at the intersection of learning and logic, join us and help shape this transformational initiative.

Key job responsibilities

• Design and implement scalable, production-grade neuro-symbolic systems that integrate formal reasoning with GenAI to deliver reliable, verifiable outcomes for AWS customers.
• 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.
• Proactively identify and pursue new opportunities to apply formal reasoning solutions across AWS services and customer domains, driving adoption and expanding the impact of neuro-symbolic approaches.
• 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.
• Mentor junior scientists and engineers, providing technical guidance, fostering a culture of scientific rigor, and raising the bar across the team.
• 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.

About the team

You will be working with a team of formal methods and machine learning specialists spanning recently hired PhDs to industry veterans. You will work collaboratively to deliver results in the form of new features for Automated Reasoning checks that delight our customers.

Basic Qualifications

• PhD, or Master's degree and 5+ years of applied research experience
• Experience programming in Java, C++, Python or related language
• 5+ years of industry or academic work in formal verification, program analysis, constraint-solving or theorem proving experience

Preferred Qualifications

• Experience delivering results for large, cross-functional initiatives/projects
• Experience working with Data & AI related technologies, including, but not limited to, AI/ML, GenAI, Analytics, Database, and/or Storage
• Experience in communicating technically, at a level appropriate for the audience
• Experience in formal verification, program analysis, constraint-solving, symbolic execution, model checking, SAT/SMT solver implementation and applications, mechanical theorem and/or code-reasoning languages such as Lean