Research Engineer/Scientist on the UK AI Security Institute's Alignment Red Team: researching and running pre-deployment evaluations to detect misalignment in frontier LLMs (deceptive alignment, reward-seeking, research sabotage), and building evaluation software and tooling. Core stack is Python with ML/eval frameworks like PyTorch and Inspect; findings are shared with frontier labs and governmen
Sign in to see your match
Connect over MCP — free, no account needed to search.