Formal Verification Scientist (Lean 4 & Mathlib)
What if your deep mathematical training could directly shape how AI understands and reasons about formal proof? We're looking for Formal Verification Scientists to translate advanced mathematical arguments into machine-verifiable Lean 4 proofs — working at the very edge of what proof assistants can express, capture, and automate. This is a fully remote, flexible contract role for mathematicians who are passionate about formal verification and want their expertise to matter in cutting-edge AI research.
Responsibilities
- Translate informal mathematical proofs into precise, machine-verifiable formalizations in Lean 4
- Analyze proofs across domains — identifying gaps, hidden assumptions, and formalizable sub-structures
- Push the boundaries of existing proof assistants, especially where automated tools struggle or fail
- Develop highly readable, reproducible proof scripts aligned with mathematical best practices and Lean idioms
- Collaborate with researchers to design and refine formal verification strategies for AI training pipelines
- Provide expert guidance on proof decomposition, lemma selection, and structuring techniques
- Investigate where and why automated provers break down — articulating failure modes clearly and constructively
- Create Lean proofs that surface deeper patterns or generalizations implicit in the original mathematics
Requirements
- Hold a Master's degree or higher in Mathematics, Logic, Theoretical Computer Science, or a closely related field
- Possess a strong foundation in rigorous proof writing across areas such as algebra, analysis, topology, logic, or discrete mathematics
- Have hands-on experience with Lean (Lean 3 or Lean 4), Coq, Isabelle/HOL, Agda, or a comparable formal proof system — Lean 4 strongly preferred
- Genuinely enthusiastic about formal verification, proof assistants, and the future of mechanized mathematics
- Able to translate dense, informal arguments into clean, structured, and correct formal proofs
- Comfortable working independently on complex, open-ended problems
Nice to Have
- Familiarity with type theory, the Curry-Howard correspondence, and proof automation techniques
- Experience contributing to or working within large-scale formalization projects such as Mathlib
- Exposure to theorem provers in settings where automated reasoning frequently requires manual scaffolding
- Prior experience with data annotation, evaluation systems, or AI training workflows
- Strong communication skills for documenting formalization decisions, edge cases, and reasoning strategies
About You
The ideal candidate is a mathematically mature problem-solver who finds genuine satisfaction in taking a dense, elegant human argument and expressing it in a form a machine can verify. You appreciate precision and structural beauty, and you're energized — not frustrated — by the gaps that automated tools cannot yet bridge. You want your mathematical expertise to contribute to something that matters.
Benefits
- Work at the frontier of formal verification and AI research alongside world-leading research labs
- Fully remote and flexible — work when and where it suits you
- Freelance autonomy with the structure of meaningful, technically demanding work
- Gain direct exposure to how advanced LLMs are trained and evaluated on mathematical reasoning
- Contribute to a rapidly evolving field where your work has lasting impact
- Potential for ongoing work and contract extension as new projects launch
Organization: Alignerr
Type: Hourly Contract
Location: Remote
Commitment: 10–40 hours/week