ML Evaluator — Code Generation Quality
Mercor (Foundation model client) · Remote
Source
Mercor (curated)
Payout
$60-85/hr
Hours/wk
10-25
Category
engineering
About the gig
Score pairs of LLM-generated code completions on correctness, idiomaticity, and security. Languages: TS, Python, Go, Rust. Detailed rubric provided. Expect 15-30 evaluations per hour.
Requirements
Code ReviewPythonTypeScriptML Evaluation
Why you might fit
- You're comfortable with Code Review, Python, TypeScript.
- Your hourly floor is around $60-85/hr and you want async-friendly work.
- You can commit 10-25 hrs/week and want a engineering engagement.
Get a cover-letter draft for this gig
Paste your skills + rate floor once. We pre-draft a Mercor-style cover letter for this posting and put it in your inbox. You edit, copy, and paste into Mercor — we don’t submit anything on your behalf.
Last updated 2026-06-07. This posting is part of a hand-curated snapshot; the live Mercor listing may have changed.