SWE Coding Benchmarks & RL Environments

Posted 19 Sep 2026

$45–75/hr

Apply

Work

Remote · Task based

Experience

Mid level

Eligibility

No stated location restriction

Field

Software engineering

Skills

Software EngineeringProgrammingSoftware TestingAI Agent EvaluationCoding BenchmarksReinforcement Learning Environments

About this role

We're running a paid study to review and verify programming tasks used for testing AI agents. We need experienced software engineers to evaluate coding harnesses and assess the quality of realistic coding challenges.

Disclosure: Skillora is independent of Terac. The apply button carries our referral code, and if you are placed, Terac pays Skillora a fee. It does not change what you are paid, our ranking does not know which listings pay us, and selection is decided by Terac’s own vetting.

All AI training jobs