AlignerrDomain experts
Formal Verification Scientist (Lean 4 & Mathlib)
up to $200/hr
About this role, in Alignerr's words
What if your deepest mathematical expertise 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 — pushing the boundary of what automated reasoning can express, capture, and achieve.
What you'll do
- Translate informal mathematical proofs into precise, machine-verifiable Lean 4 formalizations with an emphasis on clarity, structure, and correctness
- Analyze domain-specific proofs to identify gaps, hidden assumptions, and formalizable sub-structures
- Construct formalizations that test the limits of existing proof assistants — especially where automated tools struggle or fail
Show all 8 itemsHide the other 5 in What you'll do
- Collaborate with AI researchers to design, refine, and evaluate strategies for improving formal verification pipelines
- Develop highly readable, reproducible proof scripts aligned with mathematical best practices and Lean idioms
- Provide guidance on proof decomposition, lemma selection, and structuring techniques for formal models
- Investigate where automated provers break down and articulate why — complexity, missing lemmas, insufficient libraries, or otherwise
- Create Lean proofs that reveal deeper patterns or generalizations implicit in the original mathematics
Candidate background
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), with Lean 4 strongly preferred — experience with Coq, Isabelle/HOL, or Agda is also valued
- Genuinely passionate about formal verification, proof assistants, and the future of mechanized mathematics
- Able to translate informal mathematical arguments into clean, structured formal proofs independently
- Comfortable working at the frontier of what proof assistants can currently express and automate
Nice to Have
Show all 5 itemsHide these 5 items in 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 significant manual scaffolding
- Prior experience with data annotation, data quality, or AI evaluation workflows
- Strong communication skills for explaining formalization decisions, edge cases, and reasoning strategies to collaborators
Quoted from selected sections of Alignerr's posting. The full posting may state other conditions. Read the full posting
A closer look
More context, when you need it.
Full job descriptionThe original posting, in Alignerr's words
Posted by Alignerr, reproduced here so you can judge the role before clicking. Original posting ↗
Formal Verification Scientist (Lean 4 & Mathlib)
About the Role
What if your deepest mathematical expertise 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 — pushing the boundary of what automated reasoning can express, capture, and achieve.
This is a fully remote, flexible contract role designed for mathematicians who thrive at the intersection of rigorous proof construction and cutting-edge AI research. If you find satisfaction in taking a dense, elegant human argument and expressing it in a form a machine can verify, this role was built for you.
- Organization: Alignerr - Type: Hourly Contract - Location: Remote - Commitment: 10–40 hours/week
What You'll Do
* Translate informal mathematical proofs into precise, machine-verifiable Lean 4 formalizations with an emphasis on clarity, structure, and correctness * Analyze domain-specific proofs to identify gaps, hidden assumptions, and formalizable sub-structures * Construct formalizations that test the limits of existing proof assistants — especially where automated tools struggle or fail * Collaborate with AI researchers to design, refine, and evaluate strategies for improving formal verification pipelines * Develop highly readable, reproducible proof scripts aligned with mathematical best practices and Lean idioms * Provide guidance on proof decomposition, lemma selection, and structuring techniques for formal models * Investigate where automated provers break down and articulate why — complexity, missing lemmas, insufficient libraries, or otherwise * Create Lean proofs that reveal deeper patterns or generalizations implicit in the original mathematics
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), with Lean 4 strongly preferred — experience with Coq, Isabelle/HOL, or Agda is also valued * Genuinely passionate about formal verification, proof assistants, and the future of mechanized mathematics * Able to translate informal mathematical arguments into clean, structured formal proofs independently * Comfortable working at the frontier of what proof assistants can currently express and automate
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 significant manual scaffolding * Prior experience with data annotation, data quality, or AI evaluation workflows * Strong communication skills for explaining formalization decisions, edge cases, and reasoning strategies to collaborators
Why Join Us
* Work on cutting-edge AI projects 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 * Contribute directly to expanding the frontier of formal verification and AI reasoning * Gain deep exposure to how advanced AI models are trained and evaluated * Potential for ongoing work and contract extension as new projects launch
Working with AlignerrPay, getting started and work, from Alignerr's own pages
What the platform publishes in general. These are not extra terms confirmed for this particular role.
- Getting paid
- Billed weekly, Monday to Sunday, with approved work paid by the following Friday, according to Labelbox's help center. Payment goes through Stripe Connect or PayPal depending on your location, with one provider per country. intercom.help/labelbox/en/articles/13600616-alignerr-paym..., alignerr.com/process
- Before your first paid task
- Sign up, apply, verify your identity, set up billing and onboard. Some jobs add a Zara AI interview or domain assessments. alignerr.com/process
- How much work
- Time to your first project depends on demand and your skills, and there is no minimum number of hours. alignerr.com/faqs
- Contract
- Independent contractor, under terms with ALIGNERR LLC. alignerr.com/faqs, alignerr.com/privacy
Read on the pages linked above on 24 Sep 2026. Platforms change these terms, so check the linked page before you rely on one.
How does the pay compare?Across Domain experts roles, not this role alone
From our own daily reads of every open listing on the platforms we follow, not from Alignerr's posting. How we count.
Pay across the field: Domain experts
Across 699 roles in this field with a stated hourly rate in US dollars, on 18 platforms, the middle half pays $65 to $130 an hour at the top of the range, and the median is $100. This role's top rate, $200, is in the top quarter. Of the 261 distinct rates we count, 236 are lower and 15 are higher.
| Platform | Roles | Top of range, per hour |
|---|---|---|
| Alignerr (this platform) | 148 | $24 to $200 · median $80 |
| micro1 | 136 | $28 to $400 · median $110 |
| AfterQuery | 88 | $45 to $175 · median $100 |
| Handshake AI | 79 | $30 to $300 · median $85 |
| Mercor | 78 | $55 to $450 · median $120 |
Sources and listing historyWhere this information comes from
This listing's history
- First seen here on 27 Aug 2026, and still on Alignerr's list when we last read it on 13 Oct 2026.
- The listed pay has not changed since then.
- Posted by Alignerr
- First seen by AIPayList
- Last seen live
- Listing ID
- 02d56677-0b75-40ce-9a67-fe2000af7323
Pay as the source states it: “$170-200/hr”.
Platforms sometimes change a rate after posting. Every listing here is re-read at least once a day and corrected when its source moves, so a difference you see on the platform is usually a change made since the last read. How freshness works.
Keep exploring
More like this
Related field, different requirements. Check each role's own page before you apply.