{"schemaVersion":"jobsearcher.job.v1","id":"33b89a9e16cebc8d7205cbf1","url":"https://jobsearcher.com/jobs/33b89a9e16cebc8d7205cbf1","canonicalUrl":"https://jobsearcher.com/jobs/33b89a9e16cebc8d7205cbf1","title":"Machine Learning Engineer, Safety","description":"Machine Learning Engineer, Safety | Stealth Mode Frontier AI Lab | Bay AreaI'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.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.What you'd work onEvaluation and oversight systems for advanced reasoning and agentic behaviourRed-teaming and adversarial testing - turning findings into real model and training improvementsSafety-focused post-training, reward modelling, and guardrailsIdentifying and mitigating failure modes in complex, multi-step reasoningYou might be a fit if you haveStrong ML engineering skills and hands-on experience with LLMs / foundation modelsWork in one or more of: post-training (SFT/RL/RLHF), evals, red-teaming, alignment, or safety infrastructureA bias toward shipping and owning problems end-to-end in an ambiguous environmentReal interest in the hard problems of frontier AI safetyDetailsBay Area, hybridSmall, senior, talent-dense team - real ownership from day oneHighly competitive compensation","company":"Harrison Clarke","rawCompany":"harrison clarke","city":"Millbrae","state":"CA","isRemote":false,"isActive":true,"createdAt":"2026-09-20T03:54:05.515Z","occupations":[{"code":"15-2051.00","title":"Data Scientists","slug":"data-scientists"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"}],"industries":[{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"513210","title":"Software Publishers","slug":"software-publishers"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Machine Learning Engineer, Safety","description":"Machine Learning Engineer, Safety | Stealth Mode Frontier AI Lab | Bay AreaI'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.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.What you'd work onEvaluation and oversight systems for advanced reasoning and agentic behaviourRed-teaming and adversarial testing - turning findings into real model and training improvementsSafety-focused post-training, reward modelling, and guardrailsIdentifying and mitigating failure modes in complex, multi-step reasoningYou might be a fit if you haveStrong ML engineering skills and hands-on experience with LLMs / foundation modelsWork in one or more of: post-training (SFT/RL/RLHF), evals, red-teaming, alignment, or safety infrastructureA bias toward shipping and owning problems end-to-end in an ambiguous environmentReal interest in the hard problems of frontier AI safetyDetailsBay Area, hybridSmall, senior, talent-dense team - real ownership from day oneHighly competitive compensation","datePosted":"2026-09-20T03:54:05.515Z","dateModified":"2026-09-20T03:54:05.515Z","hiringOrganization":{"@type":"Organization","name":"Harrison Clarke","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"33b89a9e16cebc8d7205cbf1"},"url":"https://jobsearcher.com/jobs/33b89a9e16cebc8d7205cbf1"}}