A leading AI data company is building a benchmark of expert-written problems that test whether frontier AI agents can solve hard, real-world problems on a computer. We're looking for senior practitioners in Operations, Claims (including medical claims), Compliance, Supply Chain, Logistics, and Marketing Econometrics to design PhD-level problems drawn from their own field — the kind of problem that today's best AI tools still get wrong.
You bring the domain expertise; you don't need to be a programmer. After you submit a problem, a technical reviewer builds the code files from your work.
What You'll Do
- Create one very hard, original problem at a time within your assigned domain (and subdomain, where one is given)
- Design problems that genuinely need a computer — solved by running commands or scripts on a Linux machine, not by hand or with a calculator
- Ensure each problem has one clear, objectively correct answer that a program can mark right or wrong, so two experts working independently reach the same result
- Confirm that leading AI tools fail to solve your problem
- Stay within your assigned field, and flag any task outside your comfort zone through the support channel rather than forcing it
What You Bring
- 9+ years of professional experience in at least one of: Operations, Claims (including medical claims), Compliance, Supply Chain, Logistics, or Marketing Econometrics
- Expert-level, PhD-caliber depth in your specialty — you know where the hard, non-obvious problems live
- Experience with data-driven, computational work in your field (e.g., large claims datasets, inventory or network optimization, regulatory testing, marketing-mix models)
- Precise written communication: you can specify a problem so tightly that only one answer is correct
Nice to Have
- Hands-on experience with SQL, Python, R, or similar analytical tools
- Prior experience writing benchmarks, evaluation tasks, or expert problems for AI labs
- An advanced degree (MS, MBA, PhD) or professional certification in your domain (e.g., APICS/ASCM, CPC/CCS, CRCM/CAMS, CFA)
- Experience reviewing or quality-checking other experts' technical work
Operations & Finance Domain Expert — AI Benchmark Problem Author employer: Toptal
Toptal is an exceptional employer that fosters a dynamic and innovative work culture, perfect for those looking to make a significant impact in the marketing landscape. With a strong emphasis on employee growth and development, team members are encouraged to explore new ideas and leverage cutting-edge AI solutions, all while enjoying the flexibility of a hybrid work environment. Joining Toptal means being part of a forward-thinking team that values collaboration and creativity, making it an ideal place for professionals eager to drive enterprise growth.
