Board Game Reasoning Expert at Turing

Board Game Reasoning Expert | Contractor | Worldwide Remote

Join Turing — one of the world's fastest-growing AI companies — and help shape the next generation of large language models (LLMs). As a Board Game Reasoning Expert, you'll apply your strategic thinking, game mechanics knowledge, and analytical skills to create and evaluate high-quality AI training datasets. This is a 2-month remote contractor engagement requiring at least 20 hours per week.

About Turing

Turing accelerates the development of powerful AI systems by partnering with leading AI labs to improve LLM reasoning, problem-solving, and decision-making through expert human feedback, evaluation, and training data.

What You'll Do

• Create and review game-based reasoning tasks designed to evaluate AI systems.
• Analyze board game scenarios, strategic decision trees, and rule-based systems.
• Evaluate AI-generated responses for correctness, consistency, and reasoning quality.
• Develop prompts, rubrics, and evaluation guidelines for strategy-focused tasks.
• Identify logical errors, rule violations, and flawed reasoning in AI outputs.
• Contribute to benchmark creation and quality assurance for AI evaluation projects.
• Collaborate with project teams to improve dataset quality and evaluation methodologies.

Required Qualifications

• Bachelor's degree in Computer Science, Mathematics, Cognitive Science, Game Design, Philosophy, Economics, or a related analytical field.
• 2+ years of professional or semi-professional experience in board game design, playtesting, tabletop game communities, or strategy-focused environments.
• Strong understanding of logic, probabilistic reasoning, game mechanics, and complex rule systems.
• Background in game theory, behavioral economics, decision science, or formal logic.
• Familiarity with modern board games, TCGs, tabletop RPGs, or competitive game systems.
• Excellent analytical, problem-solving, and written communication skills.

Preferred Qualifications

• Experience in data annotation, AI training, prompt engineering, QA, or rules-based system analysis.
• Experience creating evaluation rubrics, benchmark datasets, or QA frameworks.
• Proficiency in Python, SQL, or data analysis tools.
• Familiarity with RLHF, model evaluation, synthetic data generation, or LLM benchmarking.
• Ability to quickly learn new rule systems and stay current with strategy/tabletop games.

Engagement Details

• Type: Contractor (no medical/paid leave)
• Duration: 2 months (expected start: next week)
• Commitment: Minimum 20 hours/week, at least 4 hours/day with 4-hour PST overlap
• Environment: Fully remote