JOBSEARCHER

Research Scientist, Verified Code Generation, DeepMind

ARCHIVED
GoogleSan Jose, CAL6 LeadSeptember 15th, 2026

We can't find an active application page for this role right now. It may reopen or be listed elsewhere. Use Next Steps to search for an active apply link and similar live jobs.

Overview: In this role you will advance AI agents that generate formally verified code, algorithms, and proofs using Lean. You will formalize language semantics in Lean and develop verified static analyses on top of these formalizations. You will design experiments to evaluate AI-driven proof search, benchmarking against open problems and real-world codebases. You will build scalable verification infra, translating code, orchestrating proof search, and integrating with internal Google tools and models. This position offers the chance to shape scalable formal verification at AI scale and contribute to safe, high-impact AI research. Compensation / Benefits 15% bonus targetequitybenefits
Responsibilities: Develop and improve AI agents for generating formally verified code, algorithms, and proofsFormalize programming language semantics (e.g., C/C++) in Lean and build verified static analysesDesign and run experiments evaluating AI-driven proof search, benchmarking on open problems and real-world codeBuild infrastructure for scalable formal verification, including code translation, proof search orchestration, and tooling integrationCollaborate with cross-functional teams and integrate with Google-internal tools and models
Key requirements: PhD in programming languages, formal methods, or related area (or equivalent practical experience)4 years of experience with real-world software verification and bug-finding 3 years of experience with proof assistants (Lean, Rocq, or similar) or SMT-solversLeanRocqSMT-solversformalizing semantics of real-world languagesverified static analysesproof search infrastructure