Formal Verification Scientist (Lean 4 & Mathlib)
Indexed description
This is a fully remote, flexible contract role built for mathematicians who are passionate about formal verification and want their work to matter. You'll collaborate with leading AI research teams, helping define the frontier of mechanized mathematics.
- Organization: Alignerr
- Type: Hourly Contract
- Location: Remote
- Commitment: 10–40 hours/week
- Translate informal mathematical proofs into clean, structured, machine-verifiable Lean 4 formalizations
- Analyze proofs across domains — identifying gaps, hidden assumptions, and formalizable sub-structures
- Construct formalizations that stress-test the limits of existing proof assistants, especially where automation fails
- Collaborate with AI researchers to design and refine formal verification strategies and pipelines
- Develop readable, reproducible proof scripts aligned with mathematical best practices and Mathlib idioms
- Provide expert guidance on proof decomposition, lemma selection, and structuring techniques
- Investigate where automated provers break down — and articulate exactly why
- Create Lean proofs that surface deeper patterns and generalizations implicit in the original mathematics
- Master's degree or higher in Mathematics, Logic, Theoretical Computer Science, or a closely related field
- Strong foundation in rigorous proof writing across algebra, analysis, topology, logic, or discrete mathematics
- Hands-on experience with Lean (Lean 3 or Lean 4), Coq, Isabelle/HOL, Agda, or comparable proof assistants — Lean 4 strongly preferred
- Deep enthusiasm for formal verification and the future of mechanized mathematics
- Able to translate dense, informal arguments into structured, precise formal proofs
- Mathematically mature and comfortable working at the boundary of what tools can currently express
- Experience with large-scale formalization projects such as Mathlib
- Familiarity with type theory, the Curry-Howard correspondence, and proof automation tools
- Exposure to theorem provers where automated reasoning frequently fails or requires manual scaffolding
- Prior experience with data annotation, evaluation, or quality systems
- Strong communication skills for explaining formalization decisions, edge cases, and reasoning strategies
- Work alongside world-leading AI research labs on genuinely frontier problems
- Fully remote and flexible — work when and where it suits you
- Freelance autonomy with meaningful, intellectually rich work
- Direct exposure to how cutting-edge AI models are trained and evaluated
- Contribute to work that expands what machines can understand and verify
- Potential for ongoing work and contract extension as new projects launch
Create a free Caio profile to unlock more results and save your role and location preferences.
Unlock free search