Remote contract role identifying and mitigating safety risks in conversational AI systems.
Conduct applied research to measure and reduce risks in conversational and agentic AI products. You'll design threat models, run adversarial evaluations, build Python testing pipelines, and work with engineering teams to embed safety measures into product development. Requires hands-on experience shipping safety work for real ML systems, strong coding and data analysis skills, and ability to operate independently on ambiguous problems.
Membership is €29/month, cancel anytime: every rate, every original listing link, and a daily alert for roles matching your filters.
Found at a specialist agency · listed 29 August 2026 · InsideJobs links you to the original posting.