Location
London

Hours
Full Time

Salary
Competitive, based on experience

About the Role
The Agentic Automated Reasoning Group is building the next generation of software verification tools by combining advances in artificial intelligence, cloud computing, and deep domain expertise. Join us to be part of this transformational endeavor. The Strata team is seeking an applied scientist with broad expertise in model checking, interactive theorem proving, programming language semantics, and generative AI. You will collaborate with coworkers to develop innovative tools that solve complex code analysis problems previously considered beyond reach. Our applications range from Infrastructure as Code to high-performance cryptography written in assembly, using methods from interactive theorem proving to automated test generation.

Every day, hundreds of thousands of developers perform billions of transactions worldwide on AWS, leveraging the cloud to enable innovative applications and businesses. Using automated reasoning and mathematical proofs, AWS provides provable security—absolute assurance in the security, availability, durability, and correctness of the cloud.

Key responsibilities include working with customer teams to understand their software and verification needs, identifying appropriate tools and methods including novel analysis capabilities, applying techniques from property-based testing to model checking and theorem proving, and exploring generative AI techniques to help formalize requirements, generate tests and boilerplate code, and repair program proofs.

About the Team
The Agentic Automated Reasoning Group at AWS develops and applies state-of-the-art formal methods and automated reasoning techniques to ensure the security, reliability, and correctness of AWS services and customer applications, with a strong focus on AI-based agents. Our work innovates tools and services to perform verification at scale and build safe, secure systems. We are also pioneering formal verification and automated reasoning to develop agentic systems that ensure AI agents operate within defined safety boundaries.

Experience
- Programming experience in Java, C++, Python or related languages
- Experience with neural deep learning methods and machine learning
- Experience building machine learning models for business applications
- Experience in applied research

About You
You are passionate about advancing software verification through AI and formal methods. You enjoy collaborating with diverse teams to solve challenging problems and have a strong interest in combining automated reasoning with generative AI techniques. You are motivated to innovate and apply cutting-edge research to real-world cloud security and correctness challenges.

Qualifications
- Master's degree or higher in Computer Science, Engineering, or a related field
- Preferred experience with modeling tools such as R, scikit-learn, Spark MLLib, MxNet, Tensorflow, numpy, scipy
- Preferred experience with large scale distributed systems such as Hadoop, Spark