Job Description

Gramian Consultancy is a boutique consultancy specializing in IT professional services and engineering talent solutions. With a strong background in software engineering and leadership, we help companies build high-performing teams by matching them with professionals who truly fit their needs.

Role Overview

We are seeking a mathematics-focused professional to support an advanced AI research initiative developing high-quality STEM coding datasets. In this role, you will create rigorous mathematical problems, implement verified Python solutions, and develop evaluation tests designed to assess the capabilities of frontier AI models. The position combines mathematical problem-solving, scientific programming, and AI quality evaluation, with a strong emphasis on accuracy, determinism, and first-submission quality.

CONTRACT: Contractor assignment, 4 weeks

COMMITMENT: Hourly, up to 40h/week

LOCATIONS: Remote - Bangladesh, Brazil, Colombia, Egypt, Ghana, India, Indonesia, Pakistan, Turkey, Vietnam

PROCESS: Interest Check Form, CV and Google Scholar review

Key Responsibilities

• Author mathematical coding tasks containing one main problem and at least 3 logically connected sub-problems that progressively build toward the main solution.
• Implement verified golden solutions in Python with complete unit test coverage.
• Design discriminative test cases that distinguish correct from incorrect AI-generated outputs.
• Perform quality control validation using the Central Task Platform (CTP), including Tier 1 structure checks and Tier 2 quality rubrics.
• Refine problem specifications, solutions, and test cases based on QC feedback.
• Optimize tasks to meet Pass@K evaluation criteria across multiple LLM judges, including GPT, Gemini, and Nemotron.
• Ensure mathematical correctness, well-posedness, determinism, and compliance with project quality standards.
• Maintain high first-submission quality and minimize rework, targeting consistent L1 approval.
• Participate in review sessions, feedback meetings, and project standups during required overlap hours.

Requirements