Research Scientist (AI Behaviours)
TLDR: We're looking for a research scientist to study how LLM agents fail in the wild, who can elicit deception, misalignment, and unsafe behaviour in concrete experiments, and build out the understan...
Explore 2 active Misalignment job openings aggregated from hundreds of sources. Roles range from entry-level to executive, remote and on-site, refreshed hourly.
Sign up to save jobs, get alerts, and see your CV match score.
TLDR: We're looking for a research scientist to study how LLM agents fail in the wild, who can elicit deception, misalignment, and unsafe behaviour in concrete experiments, and build out the understan...
TLDR: We're looking for a research engineer to build and maintain our internal suite of benchmarks, covering single/multi-turn content and agentic guardrails. The research engineer would also work wit...
Sign up to save jobs, get personalized alerts, and tailor your CV for better matches.