External Research Collaborator, Formal Mathematics – AI
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
External Research Collaborator building AI pipelines that convert mathematics into verified Lean 4 code. Supporting RWS’s mission to unlock global understanding through language and content technology.
Responsibilities:
- Develop, scale, and maintain multi-agent AI pipelines translating complex mathematical texts into verified Lean 4 code
- Evaluate pipeline performance and diagnose verification and compilation failures
- Implement engineering solutions to improve autoformalization reliability
- Research and implement automatic tactic generation and domain-specific proof-search strategies
- Expand and curate the client’s dataset by formalizing missing mathematical results, theorems, and proofs
- Conduct peer reviews of AI-generated Lean statements and proofs
- Ensure mathematical faithfulness, proof integrity, logical validity, and code quality
- Promote idiomatic, modular reuse of the Mathlib library
- Collaborate with global mathematics, Lean, and Mathlib open-source communities
- Support domain-specific formalization projects in areas such as algebra, analysis, and topology
- Develop evaluation methodologies to benchmark machine-learning-driven formal reasoning tools
Requirements:
- Ph.D. or Master’s degree in Mathematics, Computer Science, or a closely related quantitative field with a strong focus on formal methods, mathematical logic, or theoretical computer science
- Exceptional mathematical foundation with ability to understand, translate, and verify graduate-level mathematical proofs
- Hands-on practical experience writing formal proofs in Lean 4
- Familiarity with the design and structure of Mathlib
- Strong software engineering fundamentals in Python
- Experience working with LLMs, prompt engineering, and multi-agent developer tools
- Ability to manage open-ended research and engineering projects independently in a remote or collaborative setting
- Preferred: Active contributor to Mathlib or other formal proof repositories such as Coq or Isabelle/HOL
- Preferred: Background in Machine Learning for Code, Automatic Theorem Proving, or reinforcement learning for symbolic reasoning
- Preferred: Familiarity with compiler design, AST manipulation, or parser development in the context of Lean
- Preferred: Strong track record of open-source software contributions or research publications in formal methods, AI, or mathematics
Benefits:
- Equal employment opportunity and non-discrimination policy
- Inclusive work environment focused on diversity and career growth
- Opportunity to collaborate with global mathematics, Lean, and Mathlib open-source communities
- Remote or collaborative working setting
- Professional and research collaboration opportunities
Similar Jobs
Senior AI Agent Engineer
Senior AI Agent Engineer building Rumor Avenue's new AI product from scratch. Developing Python/FastAPI backend, React interfaces, and production LLM features.
AI Safety Expert, English – Kannada
AI safety red-teaming specialist probing frontier models for Mercor. Generating adversarial test data, vulnerability analyses, and reproducible attack artifacts for AI labs and enterprises.
AI Safety Expert, English, Punjabi
AI safety red teamer probing Mercor-trained AI models through adversarial English and Punjabi testing. Generating vulnerability annotations, attack cases, datasets, and reproducible reports.
AI Safety Expert – English, Odia
AI safety expert red-teaming Mercor’s frontier AI models through adversarial testing and human-data generation. Evaluating vulnerabilities in English and Odia across flexible, fully remote contract projects.
AI Safety Experts – English, Telugu
AI red-teaming contractor probing Mercor’s frontier models with adversarial inputs. Generating human-labeled safety data, vulnerability reports, datasets, and attack cases.
AI Safety Expert – English, Punjabi
AI red-teaming expert probing Mercor customer models with English and Punjabi adversarial inputs. Annotating vulnerabilities and producing reproducible safety datasets and attack reports.
AI Workforce Planning Consultant
Consultoría de planificación laboral con IA para rediseñar organizaciones en Ethikos. Análisis de roles, capacidades y tareas para transformar el trabajo futuro.
AI Enablement Facilitator
AI Enablement Facilitator helping Scale Army, an international staffing agency, sell and deliver AI implementation pods to U.S.-based companies. Facilitating executive workshops, live AI builds, and roadmap closes.
AI Enablement Engineer
AI Enablement Engineer building secure production AI tools, agents, and workflows for Revalize’s manufacturing technology platform. Integrating LLM systems with Salesforce, Microsoft 365, and enterprise workflows.
Business Applications & AI Technical Consultant
Remote technical consultant delivering Microsoft Dynamics 365, Power Platform, Fabric, Azure, and AI solutions. Traveling nationally to customer locations as project needs require.
AI Innovation Associate
AI Innovation Associate building LLM, agentic AI and machine-learning solutions for Aculocity’s global industrial businesses. Working remotely on real enterprise data and business challenges.
AI Safety Expert – English, Telugu
AI safety red teamer probing conversational models for Mercor’s human-data AI training projects. Generating reproducible vulnerability data to strengthen frontier AI systems.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor, which partners with AI labs to train and enhance AI systems. Identifying jailbreaks, safety failures, and vulnerabilities.
AI Safety Expert – English, Assamese
AI red-teaming expert probing conversational models for Mercor, which partners with AI labs to train frontier systems. Generating adversarial data, vulnerability classifications, and reproducible attack artifacts.
AI Safety Expert, English, Odia
AI safety red teamers probing conversational AI models for vulnerabilities. Generating human data and reproducible attack artifacts for Mercor’s AI lab and enterprise customers.
Accounting, Data, and Artificial Intelligence Internship
Estagiário de Contabilidade preparando dados financeiros para IA e automação. Instituto Infnet, faculdade brasileira focada em tecnologia, dados, comunicação e design.
AI Safety Red Teamer
AI Safety Red Teamer identifying vulnerabilities in frontier AI systems for Mercor. Designing adversarial prompts and evaluating high-risk model behavior.
AI Safety Red Teamer
AI Safety Red Teamer stress-testing frontier AI models for Mercor. Identifying vulnerabilities and improving model alignment through adversarial evaluation.
AI Safety Expert, English – Bengali
AI red-teaming experts probing conversational models for Mercor, which helps AI labs train frontier systems. Testing vulnerabilities and producing reproducible safety data in English and Bengali.
AI Safety Experts – English, Odia
AI safety expert red-teaming conversational AI models for Mercor’s frontier-model training projects. Generating vulnerability annotations, attack cases, datasets, and reproducible safety reports.