The work

You will turn realistic situations from reliability, quality, process or test engineering into self-contained analysis problems for frontier AI evaluation. Day to day, that means defining the engineering context, supplying usable data and assumptions, solving each problem step by step, and documenting the reference answer, including mistakes that may appear statistically plausible but fail in practice.

What afterquery screens for

The platform screens for at least three years of full-time experience in a relevant engineering role, hands-on use of design of experiments, statistical process control or reliability analysis, and fluency with at least one of Minitab, JMP, Python or R. Expect follow-up on specific projects, method selection, assumptions, interpretation, and how you would judge an AI answer that reaches a superficially reasonable conclusion. Strong written English is required.

Logistics

This is a remote, fully asynchronous independent contractor role with no fixed schedule. You must be able to commit at least 10 hours per week, there is no maximum, and workload can scale up or down from week to week. Ongoing project work is paid weekly through Stripe, with no screen recording, keystroke monitoring or idle timers.

Pay band: $115/hr