AI Evaluation jobs
5 open roles for ai evaluation, updated continuously as employers post them.
Freelance Agent Evaluation Engineer
A remote, freelance role designing tasks and tests that evaluate AI coding agents, paid per accepted task up to $40/hr, for developers with 5+ years of experience.
Machine Learning (ML) AI Task Auditor - Freelance AI Trainer Project
Invisible is seeking remote freelance machine learning specialists to audit tasks used in AI training and evaluation. The work suits experienced ML practitioners who can test complex workflows and identify data, model, and algorithmic problems.
Software Engineer
Agency is seeking remote freelance software engineers to audit SWE-Bench tasks used in AI training and evaluation. The project fits experienced engineers who can rigorously test complex tasks and provide precise technical feedback.
Clinical, Biomedical & Pharmaceutical Specialist (Remote | $80–$120/hr)
This remote evaluator contract is for experienced clinical, biomedical, and pharmaceutical professionals reviewing AI-generated materials. Candidates need strong domain judgment, writing ability, and presentation-tool proficiency.
Clinical Research & Pharmaceutical Specialist (Remote | $80–$120/hr)
A remote contract for clinical, biomedical, and pharmaceutical specialists who can evaluate AI-generated work and provide rigorous written feedback. It suits professionals with at least five years of domain experience and strong document-review skills.