Join the Appen team as an Independent Contractor for Project Astra . Project Astra is seeking individuals for an ongoing, ad-hoc project focused on improving real-time conversational AI.
Formal Verification Scientist (Lean 4 & Mathlib)
Job description
Formal Verification Scientist (Lean 4 & Mathlib)
About the Role
What if your deep mathematical training could directly shape how AI reasons about truth, proof, and knowledge? We're looking for Formal Verification Scientists to translate advanced mathematical arguments into machine-verifiable Lean 4 proofs — working at the precise intersection of rigorous mathematics and cutting-edge AI research.
This is a fully remote, flexible contract role designed for mathematicians who love precision and thrive at the frontier of what proof assistants can express, capture, and automate.
- Organization: Alignerr
- Type: Hourly Contract
- Location: Remote
- Commitment: 10–40 hours/week
What You'll Do
- Translate informal mathematical proofs into clean, structured, machine-verifiable Lean 4 formalizations
- Analyze proofs across domains — identifying gaps, hidden assumptions, and formalizable sub-structures
- Push the boundaries of existing proof assistants by working on problems that lie beyond current automation capabilities
- Collaborate with AI researchers to design and refine formal verification pipelines
- Develop readable, reproducible proof scripts aligned with mathematical best practices and Lean idioms
- Provide expert guidance on proof decomposition, lemma selection, and structuring strategies for formal models
- Investigate where automated provers break down — and articulate precisely why
- Uncover deeper patterns and generalizations hidden within classical mathematical arguments
Who You Are
- 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 proof assistant — Lean strongly preferred
- Genuinely excited about formal verification, proof assistants, and the future of mechanized mathematics
- Able to take a dense, informal argument and express it precisely in a form a machine can verify
- Self-directed and comfortable working independently on complex, open-ended problems
Nice to Have
- Familiarity with type theory, the Curry-Howard correspondence, and proof automation tools
- Experience contributing to large-scale formalization projects such as Mathlib
- Exposure to theorem provers where automated reasoning frequently fails or requires manual scaffolding
- Prior experience with data annotation, quality evaluation, or AI training workflows
- Strong communication skills for explaining formalization decisions, edge cases, and proof strategies
Why Join Us
- Work directly on cutting-edge AI projects alongside leading research labs
- Fully remote and flexible — work when and where it suits you
- Freelance autonomy with the depth and challenge of meaningful, frontier-level work
- Gain rare exposure to how advanced LLMs are trained to reason about mathematics
- Contribute to a growing body of machine-verifiable mathematical knowledge that will shape AI for years to come
- Potential for ongoing work and contract extension as new projects launch
You will be redirected to the company's website to complete your application.