Lean Theorem Proving Engineer, Verified Code Generation, DeepMind
Google DeepMind is a London-headquartered AI lab building frontier models and agents. They're hiring a Lean Theorem Proving Engineer to develop formally verified code generation using the Lean proof assistant, based in London on a hybrid basis. This AI engineering role sits within the UK's frontier AI sector.
Minimum qualifications:
- PhD or equivalent experience in computer science or mathematics.
- 3 years of experience with the Lean proof assistant.
- 3 years of experience with using AI agents.
Preferred qualifications:
- Experience with AI agents for code or mathematical reasoning tasks.
- Track record of publications at top research venues.
About the job
Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority.
We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort. Individual pay is determined by factors including job-related skills, experience, and relevant education or training.US: $174000 - $252000 (USD) + 15% bonus target + equity + benefits
Learn more about benefits at Google.
Responsibilities
- Formalize correctness and security specifications of complex real-world systems in Lean with AI assistance.
- Encode the semantics of programming languages (e.g., C/C++/Rust) in Lean with AI assistance.
- Design and run experiments evaluating AI-driven autoformalization and proof search applied to verification of real-world codebases.
- Build infrastructure for applying formal verification at scale, translating code, orchestrating proof search, and integrating with Google-internal tools and models.
About DeepMind
Google DeepMind is an AI research laboratory focused on building artificial general intelligence. Founded in London in 2010 by Demis Hassabis, Shane Legg, and Mustafa Suleyman, the company was acquired by Google in 2014 for approximately $660M. DeepMind pioneered breakthroughs including AlphaGo, the first program to defeat a world champion at Go, and AlphaFold, which solved the 50-year-old protein folding problem and has been used by over two million researchers worldwide. The lab remains headquartered in London with a large UK engineering presence and continues to push the boundaries of reinforcement learning, large language models, and scientific AI.