Applied Scientist, Agentic Automated Reasoning

Amazon Amazon · Big Tech · London, United Kingdom · Applied Science

This role focuses on building next-generation software verification tools by combining AI, cloud computing, and formal methods. The scientist will explore generative AI techniques for formalizing requirements, generating tests, and repairing proofs, and will work on agentic systems to ensure AI agents operate within safety boundaries.

What you'd actually do

  1. Work with customer teams to understand the nature of their software and the properties they need to establish of it.
  2. Identify tools and methods capable of addressing the verification needs of customers, including any novel analysis capabilities required.
  3. Use techniques spanning property-based testing to model checkers, and interactive theorem provers to establish program properties.
  4. Explore generative AI techniques to help customers formalize their requirements, find revealing tests, generate required boiler plate for testing and model checking, and find and repair program proofs.

Skills

Required

  • PhD, or a Master's degree and experience in CS, CE, ML or related field research
  • Experience in patents or publications at top-tier peer-reviewed conferences or journals
  • Experience programming in Java, C++, Python or related language
  • Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing
  • Experience in formal verification, program analysis, constraint-solving, or theorem proving (academic or professional work)

Nice to have

  • Experience with model checking tools and techniques, SAT/SMT solvers
  • Knowledge of one or more methods of defining semantics: operational, denotational, axiomatic, etc.
  • Experience applying machine learning and generative AI tools.

What the JD emphasized

  • software verification tools
  • generative AI
  • automated reasoning
  • agentic systems
  • formal verification
  • program analysis
  • theorem proving

Other signals

  • generative AI
  • automated reasoning
  • software verification
  • agentic systems