Board Game Reasoning Expert (AI Training & Evaluation)

What you'll do

Board games make good AI tests because they are bundles of precise rules, hidden information and long-range planning. You use that to write and review tasks that expose where a model misreads a rule, miscounts a probability or plans badly.

• Create and review game-based reasoning tasks
• Analyze scenarios, decision trees and rule systems
• Grade AI answers for correctness, consistency and reasoning quality
• Write prompts, rubrics and evaluation guidelines
• Spot logic errors and rule violations in model outputs
• Contribute to benchmarks and quality assurance

Who fits

Required:

• A 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 communities or similar strategy settings
• Strong grounding in logic, probability, game mechanics and complex rules; a game theory, behavioral economics, decision science or formal logic background
• Familiarity with modern board games, TCGs, tabletop RPGs or competitive game systems, and strong written communication

Preferred: annotation, AI training or QA experience; rubric and benchmark work; Python or SQL; RLHF or LLM benchmarking exposure; quick learning of newly released games.

What it pays

The ad does not publish a rate. Turing sets rates per project; see the company page.

Worth knowing

Good:

• A niche where hobby expertise counts as qualification
• Fully remote, with a short 2-month contract
• Start expected the following week

Less good:

• The degree and 2-year experience bar is real
• At least 4 hours a day and 20 hours a week, with 4 hours of PST overlap
• Contractor assignment with no medical or paid leave
• Selection includes a take-home assessment

About this listing

Posted on Turing's board on 11 June 2026 and read on 18 October 2026. Hours, duration and requirements are Turing's own text. See Turing.