About this opportunity
Confidential lists this Lean Engineer, Formal Mathematics opportunity in Jollyville, Texas. Review the employer’s description below for duties, qualifications and application requirements.
Job description
Help advance AI systems that can produce rigorous, machine-checked mathematics. In this role, you will write and evaluate Lean 4 proofs, translate informal mathematics into precise formal statements, and assess whether AI-generated proofs establish the intended result, not merely whether they pass the proof checker.
Role Overview You will support an AI research team working on formal mathematics, with a focus on faithful formalization, proof quality, and sound use of current mathlib conventions.
Key Responsibilities Write correct, idiomatic Lean 4 statements and proofs that compile against current mathlib across algebra, analysis, number theory, combinatorics, and logic.
Formalize natural-language mathematics, including competition problems, textbook results, and research-level lemmas, while ensuring the formal statement accurately reflects the original.
Review AI-generated Lean statements and proofs, identify failures or cases where a proof establishes the wrong claim, and provide clear written feedback.
Help develop guidelines and rubrics for proof quality, statement fidelity, and mathlib conventions.
Collaborate with Lean engineers and researchers to maintain consistent standards and improve output quality.
Qualifications Hands-on experience writing formal proofs in Lean 4, such as through mathlib contributions, formalization projects, Lean libraries or tools, or autoformalization work.
Comfort using mathlib, Lean 4 tactics, and relevant lemmas.
A strong background in proof-based mathematics, theoretical computer science, or logic through a degree or research record.
Ability to convert written mathematical statements and proofs into correct formal statements and machine-checked proofs.
Clear written communication, including the ability to explain proof strategies and formalization decisions precisely.
Preferred Experience Experience with Coq/Rocq, Isabelle, Agda, Haskell, Lean metaprogramming, or AI-for-mathematics work such as LLM provers, Lean agent environments, miniF2F, ProofNet, or PutnamBench.
Applicants do not need every preferred qualification to apply.
Work Terms Remote, hourly W-2 employment.
Commit at least 20 hours per week during weekdays, with the option to increase to 40 hours per week.
Engagement supports placement with a leading AI lab through its extended workforce.
Compensation $90 to $110 per hour.
Equal Opportunity Employment decisions are made without discrimination based on race, religion, color, national origin, sex, pregnancy, childbirth, reproductive health decisions, related medical conditions, sexual orientation, gender identity, gender expression, age, protected veteran status, disability, genetic information, political views or activity, or any other legally protected characteristic.
Who can apply
Review the original listing for work authorization, qualifications and employer requirements.