Other open roles
Senior Backend Engineer - Coding-Agent Eval
Work Expert (WE) is an independent publishing and referral website. We are not a recruiter, hiring manager, agent or employer, and we are not affiliated with or endorsed by Mercor. Applying takes you to the platform's own website, where we may be recorded as the referring source. We may receive a referral fee at no additional cost to you. Read our full affiliate disclosure →
About the Role
A frontier lab is grading its autonomous coding agent and needs experienced backend engineers to audit full execution traces and write a short judgement the training team can act on.
What You'll Do
- Step through agent runs across multi-file Python and Go repositories
- Flag reward-hacking, shortcutting and unsafe tool or shell calls
- Write a 3-5 sentence rationale per trajectory against a rubric
You're a Good Fit If You
- You have shipped and reviewed production backend code
- You can reason about correctness without running everything
- You have 5+ years of backend engineering experience
Role Highlights
Pay & Payout
Hourly, billed against reviewed and accepted trajectories. Mercor pays weekly via Stripe once your first offer is accepted and your identity is verified.
Apply on MercorOpens Mercor in a new tab. You pay nothing; we may earn a referral fee.
Similar roles
More coding work you may qualify for.
LLM Coding Trainer - Python
Produce and correct Python problem-solution pairs to fine-tune a code model; step-by-step reasoning required.
Full-Stack Reviewer - Vetting Pool
Assess candidate code submissions for a hiring pipeline; 15-25 min each, flat rate, work when tasks are live.
Quantitative Finance Expert
Score LLM answers on equities, M&A and accounting prompts against a rubric; write short rationales.