Senior Software Engineer - Agent Evaluation

About the role

Project-based freelance for Mindrift: design hard coding-agent eval tasks, simulated company environments, and tests that distinguish frontier models. Remote, paid per accepted task. For a senior SWE who can write fair automated checks.

What you'll do

• Build realistic simulated company environments for coding-agent evaluation
• Design tasks, success criteria, and tests that accept valid solutions and reject bad ones
• Iterate on evals from QA feedback until they are fair and robust
• Work project-based and remote; paid per accepted task

Requirements

• 5+ years software development; Python/FastAPI, JS/TS React, Docker, Postgres, Kafka, Redis
• Experience writing functional and integration tests
• English B2+; Master's preferred or Bachelor's plus 5 years
• Not a labeling or prompt-only role — you design agent evals

AI Alerts shares third-party job opportunities for informational purposes only. We are not the employer and are not involved in the hiring process. Always verify the company and role through official channels before applying, and never pay to apply, train, onboard, process documents, or secure a job offer. Legitimate employers do not ask applicants for money. Read our Terms to learn more.