Machine Learning Engineer, Safety

Machine Learning Engineer, Safety Stealth Mode Frontier AI Lab Bay Area\n \n I'm working with a well-funded, early-stage stealth AI lab building genuinely frontier systems - and they're hiring a Machine Learning Engineer focused on safety.\n \n The mission: make advanced AI systems reliable, controllable, and aligned as their capabilities grow.

This is hands-on, unsolved-problem work at the edge of what's possible.\n \n What you'd work on\n\n Evaluation and oversight systems for advanced reasoning and agentic behaviour\n Red-teaming and adversarial testing - turning findings into real model and training improvements\n Safety-focused post-training, reward modelling, and guardrails\n Identifying and mitigating failure modes in complex, multi-step reasoning\n\n \n You might be a fit if you have\n\n Strong ML engineering skills and hands-on experience with LLMs / foundation models\n Work in one or more of: post-training (SFT/RL/RLHF), evals, red-teaming, alignment, or safety infrastructure\n A bias toward shipping and owning problems end-to-end in an ambiguous environment\n Real interest in the hard problems of frontier AI safety\n\n \n Details\n\n Bay Area, hybrid\n Small, senior, talent-dense team - real ownership from day one\n Highly competitive compensation\n\n