Senior AI Coding Evaluator: Engineering Taste (Remote)

Openkrill; United States; A distancia; USD 138.000 - 276.000; A tiempo parcial

Descripción de la vacante

Openkrill is seeking a highly experienced software engineer to evaluate AI coding agents like Codex and Claude Code. This contract role focuses on evaluating whether models think like a top engineer, not on writing production code.

You will judge the usefulness, correctness, and engineering judgment of AI outputs in real-world scenarios, delivering structured, opinionated feedback. Strong English communication is essential.

Formación

• Senior/Staff/Principal level engineer or equivalent experience.
• Hands-on experience with at least one of Codex, Claude Code or Cursor.
• Excellent writing and verbal communication in English (B2+).

Responsabilidades

• Evaluate AI-generated coding interactions end to end.
• Provide clear, opinionated feedback on what worked and what didn’t.
• Assess explanations and reasoning, not just code quality.
• Define what great looks like when using AI coding tools.

Conocimientos

TypeScript/JavaScript

Python

Senior/Staff level

Herramientas

OpenAI Codex

Claude Code

Cursor

Descripción del empleo

Openkrill is seeking a highly experienced software engineer to evaluate AI coding agents like Codex and Claude Code. This contract role focuses on evaluating whether models think like a top engineer, not on writing production code.

You will judge the usefulness, correctness, and engineering judgment of AI outputs in real-world scenarios, delivering structured, opinionated feedback. Strong English communication is essential.