[LVAOTZ1E] Maths Expert

Hello,

Greetings from ZettaMine!!!

We are hiring Maths Experts – Task Based for a short-term AI Evaluation & Mathematical Reasoning project across: India

Role: Maths Expert – Task Based

Experience: Ph.D. in Mathematics or an equivalent technical field

Mode: Remote

Engagement: Short-Term Contract – 12 Weeks

Start: Immediate

Mandatory Eligibility Criteria

Technical Qualification:

• Strong foundation in Mathematics , covering advanced undergraduate through graduate and Ph.D.-level concepts.
• Strong analytical, research, and problem-solving skills.
• Ability to design and solve challenging, multi-step mathematical problems .
• Ability to break down complex mathematical concepts and problems into clear, structured, step-by-step reasoning.
• Strong English comprehension and written communication skills.
• Ability to evaluate complex reasoning pathways and identify errors or limitations in AI-generated solutions.
• Strong lateral and creative thinking skills to construct novel mathematical scenarios.
• Experience in AI evaluation, data annotation, content review, quality assurance, or related analytical work is preferred but not mandatory.

Educational Qualification:

Mandatory: Ph.D. / Doctorate in Mathematics or an equivalent technical field.

Preferred: Advanced research or academic experience across mathematics and the ability to work with graduate- and Ph.D.-level mathematical concepts.

Availability :

• Up to 40 hours per week .
• Minimum 4 hours of overlap with PST working hours per day .
• Immediate availability preferred.
• Commitment for the full 12-week engagement period .
• Average Task Handling Time: 4 hours .

Others:

• Personal desktop/laptop with a stable, high-speed internet connection.
• Strong ability to work independently in a remote environment.
• Excellent structured written communication and ability to provide constructive feedback and detailed annotations.
• Ability to collaborate remotely with LLM researchers and project teams.
• Talent Rate: $80 per approved task.
• Partner Fee: $150 flat.
• Total Positions:
• Engagement Type: Contractor / Short-Term Contract .
• Candidates must successfully complete the required evaluation and delivery review process.
• Vetting Process: Interest Check Form (ICF) → Assessment → Delivery Review.
• Final selected candidates will be contacted regarding onboarding and next steps.

What You’ll Work On:

• Design and solve challenging mathematics problems that test the reasoning capabilities and limitations of large language models.
• Create high-quality, step-by-step gold-standard solutions with clear and detailed reasoning.
• Develop mathematical tasks covering concepts ranging from advanced undergraduate to graduate and Ph.D.-level topics .
• Work with LLM researchers to align task designs with specific evaluation objectives.
• Identify areas where AI models struggle, including symbolic manipulation, abstraction, multi-step reasoning, quantitative analysis, logical reasoning, and complex mathematical problem-solving .
• Construct novel mathematical scenarios that test analytical and creative reasoning.
• Evaluate AI-generated solutions for mathematical accuracy, logical consistency, correctness, and quality of reasoning .
• Provide structured feedback and detailed annotations to improve AI model performance.
• Help define and develop new mathematics evaluation benchmarks .
• Contribute to benchmarks across a broad range of mathematics curricula and advanced mathematical topics.
• Support frontier AI evaluation initiatives by creating rigorous, challenging, and objectively assessable mathematics tasks.

Interested candidates: Please share your updated CV at: [email protected]

Thanks & Regards,

RaviTeja K

ZettaMine