Ai evaluation engineer: build real-world coding challenges

Mindrift is assembling a dataset and evaluation framework to test AI coding agents. You will construct realistic developer environments, including codebases, infrastructure, and contextual artifacts such as tickets and docs, to simulate a believable history.

You will design tasks from intermediate states, define solvable criteria for AI agents, and craft tests that tolerate multiple valid approaches while rejecting incorrect ones. #J-18808-Ljbffr