Researcher — AI Evaluation

• Full‑time remote role dedicated to evaluating and benchmarking AI systems across diverse tasks.
• Design and run experiments to measure performance, bias and safety, analysing results to inform model improvements.
• Collaborate with cross‑functional research teams to build evaluation frameworks and reporting pipelines.
• Ideal for candidates with strong analytical skills and experience in AI research or evaluation.

Application and compensation are controlled by Mercor. This is a referral link.