Senior AI Coding Evaluator — Remote, Part-Time

Openkrill; United States; Remote; USD 138,000 - 276,000; Part time

Job summary

Openkrill seeks a Senior/Staff engineer to evaluate AI coding agents rather than writing production code. You0ll assess whether interactions with Codex, Claude Code, or Cursor reflect strong engineering judgment and useful explanations, and provide detailed feedback.

This role is remote worldwide, part-time, 10-20 hrs/week, with hourly rate $100-$200. Start after take-home, no traditional interview, Loom walkthrough.

Qualifications

• Senior/Staff/Principal-level engineer with strong technical background
• Excellent written and spoken English (B2 or above)
• Experience with prompt design or evaluation workflows is a plus
• Comfortable giving direct, opinionated feedback

Responsibilities

• Evaluate AI-generated coding interactions end to end
• Judge usefulness and correctness at a high level
• Assess explanations and reasoning quality
• Distinguish between levels of response quality (e.g., what makes something a 2 vs a 4)
• Provide clear, opinionated feedback in writing

Skills

TypeScript/JavaScript

Python

AI-assisted dev workflows

Code evaluation

English communication

Tools

OpenAI Codex

Claude Code

Cursor

Job description

Openkrill seeks a Senior/Staff engineer to evaluate AI coding agents rather than writing production code. You0ll assess whether interactions with Codex, Claude Code, or Cursor reflect strong engineering judgment and useful explanations, and provide detailed feedback.

This role is remote worldwide, part-time, 10-20 hrs/week, with hourly rate $100-$200. Start after take-home, no traditional interview, Loom walkthrough.