{"schemaVersion":"jobsearcher.job.v1","id":"32ce8de046d48448eb57fa1d","url":"https://jobsearcher.com/jobs/32ce8de046d48448eb57fa1d","canonicalUrl":"https://jobsearcher.com/jobs/32ce8de046d48448eb57fa1d","title":"Software Engineer, Safeguards Evals","description":"About Anthropic\r\nAnthropic's mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.\r\nAbout the Role\r\nHow do we know our safety systems actually catch misuse? Anthropic increasingly uses AI to investigate potential misuse of Claude — analyzing real-world traffic to surface bad actors, policy violations, and emerging threats. Its findings inform enforcement actions and model launch decisions, which means we need rigorous, trustworthy answers to questions like: Does the monitoring agent catch what it should? Where does it fail? Does it stay reliable as adversaries adapt, as models improve, and as the agent itself changes?\r\nThis role builds the evaluation infrastructure that answers those questions. You'll sit at the intersection of applied ML research and engineering — designing experiments to measure how well an investigative agent performs across harm areas, building datasets that represent real abuse rather than synthetic benchmarks, and shipping those methods into pipelines that gate every change to the system. Your work directly determines how much trust Anthropic can place in its automated abuse detection, and where we invest to make it better.\r\nKey Responsibilities\r\nBuild and own the evaluation harness for an agentic investigation system — defining metrics, test cases, and grading approaches for a complex long-horizon agent.\r\nConstruct high-quality eval datasets representing real-world misuse across harm areas (e.g., cyber attacks, bio weapons, influence operations), drawing from real traffic patterns and synthetic generation.\r\nMeasure agent performance end-to-end (detection precision/recall, investigation quality, robustness) and drive hill-climbing on the hardest harm areas.\r\nAnalyze coverage to identify measurement gaps, and evolve evals so they remain unsaturated and high-signal as agent capabilities advance.\r\nProductionize successful research into regression and release pipelines that run on every agent change, prompt update, and underlying model upgrade.\r\nBuild tooling that enables policy experts to author, run, and iterate on evaluations without engineering support.\r\nConstruct RL environments to improve Claude's safety investigation capabilities.\r\nMinimum Qualifications\r\nProficiency in Python and comfort working across the stack.\r\nExperience building and maintaining data pipelines.\r\nExperience working with LLMs and a working understanding of their capabilities and failure modes — especially agentic systems with tool use and multi-step reasoning.\r\nStrong data analysis skills — you can draw reliable insights from large datasets.\r\nAbility to move fluidly between research prototyping and production-quality code.\r\nAbility to translate ambiguous problems into concrete, testable experiments.\r\nPreferred Qualifications\r\n6+ years of industry software engineering experience.\r\nExpertise in building or contributing to agent evaluation frameworks, benchmarks, or automated grading systems.\r\nExtensive experience in trust and safety, content moderation, or abuse detection systems.\r\nExperience in red teaming, adversarial testing, or jailbreak research on AI systems.\r\nExperience with synthetic data generation or data augmentation.\r\nExperience with distributed systems or large-scale data processing.\r\nExperience with prompt engineering or building LLM-powered applications.\r\nCompensation\r\nAnnual Salary: $320,000 — $485,000 USD\r\nLogistics\r\nMinimum education: Bachelor's degree or an equivalent combination of education, training, and/or experience.\r\nRequired field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience.\r\nMinimum years of experience: Years of experience required will correlate with the internal job level requirements for the position.\r\nLocation-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.\r\nVisa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.\r\nBenefits\r\nAnthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues.\r\nWe encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.\r\nYour safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.\r\nJ-18808-Ljbffr","company":"Aimling","rawCompany":"aimling","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-06-25T01:16:30.575Z","occupations":[{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"17-2112.02","title":"Validation Engineers","slug":"validation-engineers"}],"industries":[{"code":"513210","title":"Software Publishers","slug":"software-publishers"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Software Engineer, Safeguards Evals","description":"About Anthropic\r\nAnthropic's mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.\r\nAbout the Role\r\nHow do we know our safety systems actually catch misuse? Anthropic increasingly uses AI to investigate potential misuse of Claude — analyzing real-world traffic to surface bad actors, policy violations, and emerging threats. Its findings inform enforcement actions and model launch decisions, which means we need rigorous, trustworthy answers to questions like: Does the monitoring agent catch what it should? Where does it fail? Does it stay reliable as adversaries adapt, as models improve, and as the agent itself changes?\r\nThis role builds the evaluation infrastructure that answers those questions. You'll sit at the intersection of applied ML research and engineering — designing experiments to measure how well an investigative agent performs across harm areas, building datasets that represent real abuse rather than synthetic benchmarks, and shipping those methods into pipelines that gate every change to the system. Your work directly determines how much trust Anthropic can place in its automated abuse detection, and where we invest to make it better.\r\nKey Responsibilities\r\nBuild and own the evaluation harness for an agentic investigation system — defining metrics, test cases, and grading approaches for a complex long-horizon agent.\r\nConstruct high-quality eval datasets representing real-world misuse across harm areas (e.g., cyber attacks, bio weapons, influence operations), drawing from real traffic patterns and synthetic generation.\r\nMeasure agent performance end-to-end (detection precision/recall, investigation quality, robustness) and drive hill-climbing on the hardest harm areas.\r\nAnalyze coverage to identify measurement gaps, and evolve evals so they remain unsaturated and high-signal as agent capabilities advance.\r\nProductionize successful research into regression and release pipelines that run on every agent change, prompt update, and underlying model upgrade.\r\nBuild tooling that enables policy experts to author, run, and iterate on evaluations without engineering support.\r\nConstruct RL environments to improve Claude's safety investigation capabilities.\r\nMinimum Qualifications\r\nProficiency in Python and comfort working across the stack.\r\nExperience building and maintaining data pipelines.\r\nExperience working with LLMs and a working understanding of their capabilities and failure modes — especially agentic systems with tool use and multi-step reasoning.\r\nStrong data analysis skills — you can draw reliable insights from large datasets.\r\nAbility to move fluidly between research prototyping and production-quality code.\r\nAbility to translate ambiguous problems into concrete, testable experiments.\r\nPreferred Qualifications\r\n6+ years of industry software engineering experience.\r\nExpertise in building or contributing to agent evaluation frameworks, benchmarks, or automated grading systems.\r\nExtensive experience in trust and safety, content moderation, or abuse detection systems.\r\nExperience in red teaming, adversarial testing, or jailbreak research on AI systems.\r\nExperience with synthetic data generation or data augmentation.\r\nExperience with distributed systems or large-scale data processing.\r\nExperience with prompt engineering or building LLM-powered applications.\r\nCompensation\r\nAnnual Salary: $320,000 — $485,000 USD\r\nLogistics\r\nMinimum education: Bachelor's degree or an equivalent combination of education, training, and/or experience.\r\nRequired field of study: A field relevant to the role as demonstrated through coursework, training, or professional experience.\r\nMinimum years of experience: Years of experience required will correlate with the internal job level requirements for the position.\r\nLocation-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.\r\nVisa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.\r\nBenefits\r\nAnthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues.\r\nWe encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.\r\nYour safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.\r\nJ-18808-Ljbffr","datePosted":"2026-06-25T01:16:30.575Z","dateModified":"2026-06-25T01:16:30.575Z","hiringOrganization":{"@type":"Organization","name":"Aimling","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"32ce8de046d48448eb57fa1d"},"url":"https://jobsearcher.com/jobs/32ce8de046d48448eb57fa1d"}}