Abstract Math & Reasoning Engineer at Turing

Abstract Math & Reasoning Engineer | Contractor | 5-Week Engagement | Worldwide Remote

Turing is seeking a skilled mathematical reasoning professional to design high-quality reasoning datasets for Large Language Model (LLM) training. This role involves creating complex, formally defined mathematical systems — including novel or fictional constructs — that challenge AI models to learn, reason, and prove properties from first principles.

This is a fully remote contractor role requiring a minimum of 40 hours per week with at least 4 hours of daily overlap with PST.

About Turing

Turing is one of the world's fastest-growing AI companies, partnering with leading AI labs to advance frontier model capabilities in reasoning, coding, STEM, and beyond — while also building real-world AI systems for enterprise clients.

Key Responsibilities

• Design and define novel mathematical objects and operations inspired by abstract algebra, group theory, or entirely fictional systems (e.g., color-attributed numbers with custom arithmetic rules).
• Author multi-part reasoning tasks that evaluate an LLM's ability to interpret definitions, perform calculations, and construct valid proofs within newly defined systems.
• Develop problem types covering:
  • Applying custom mathematical rules to compute or simplify expressions.
  • Proving or disproving structural properties such as associativity, closure, and commutativity.
  • Performing symbolic manipulation within multi-layered or hybrid mathematical frameworks.
• Ensure every task includes deterministic answers, fully verified step-by-step reasoning traces, and a scoring rubric that distinguishes rule misuse, algebraic errors, and incomplete proofs.
• Anticipate and address edge cases such as undefined identities, non-associative triples, and boundary-rule ambiguities.
• Collaborate with reviewers and LLM engineers to refine task definitions, phrasing, and reproducibility standards.

Qualifications

• 2+ years of experience in a technical, mathematical, or analytical role (mathematics, computer science, logic, or data science).
• Strong background in abstract reasoning and formal mathematical systems — group theory, modular arithmetic, symbolic logic, etc.
• Proven ability to design structured reasoning problems testing both procedural and conceptual understanding.
• Excellent written communication skills for producing clear, rigorous, and logically sound task descriptions.
• Meticulous attention to detail and logical completeness in definitions and proofs.
• Experience working with or evaluating LLMs is a plus.
• Degree in Mathematics, Theoretical Computer Science, or a related STEM field preferred.

Deliverables

• A structured collection of reasoning tasks covering definition/application of new mathematical systems, proof and property reasoning, and symbolic expression evaluation.
• Each task must include:
  • A formal context block (system definition, axioms, and examples).
  • A prompt query (calculation, proof, or reasoning challenge).
  • An expected output with a step-by-step reasoning trace leading to a deterministic result.
  • A rubric for scoring correctness, consistency, and completeness.
• All tasks must be self-contained, verifiable, and aligned with model reasoning evaluation goals.

Engagement Details

• Type: Contractor Assignment
• Duration: 5 Weeks
• Hours: Minimum 40 hours/week with 4-hour PST overlap required

Evaluation Process

• Shortlisted candidates will receive a Job Interest Form.
• A timed assessment will be shared (must be completed within 48 hours).
• Successful candidates will be contacted to discuss pre-onboarding requirements.