ML/Research Engineer, Safeguards

About Anthropic\n\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.\n\n### About the role\n\nWe are looking for ML Engineers and Research Engineers to help detect and mitigate misuse of our AI systems. As a member of the Safeguards ML team, you will build systems that identify harmful use—from individual policy violations to sophisticated, coordinated attacks—and develop defenses that keep our products safe as capabilities advance. This work feeds directly into Anthropic's Responsible Scaling Policy commitments.\n\n### Responsibilities\n- Develop classifiers to detect misuse and anomalous behavior at scale. This includes developing synthetic data pipelines for training classifiers and methods to automatically source representative evaluations to iterate on\n- Build systems to monitor for harms that span multiple exchanges, such as coordinated cyber attacks and influence operations, and develop new methods for aggregating and analyzing signals across contexts\n- Evaluate and improve the safety of agentic products—developing both threat models and environments to test for agentic risks, and developing and deploying mitigations for prompt injection attacks\n- Conduct research on automated red-teaming, adversarial robustness, and other research that helps test for or find misuse\n\n### You may be a good fit if you\n- Have 4+ years of experience in ML engineering, research engineering, or applied research, in academia or industry\n- Have proficiency in Python and experience building ML systems\n- Are comfortable working across the research-to-deployment pipeline, from exploratory experiments to production systems\n- Are worried about misuse risks of AI systems, and want to work to mitigate them\n- Have strong communication skills and ability to explain complex technical concepts to non-technical stakeholders\n\n### Strong candidates may also have experience with\n- Language modeling and transformers\n- Building classifiers, anomaly detection systems, or behavioral ML\n- Adversarial machine learning or red-teaming\n- Interpretability or probes\n- Reinforcement learning\n- High-performance, large-scale ML systems\n\nThe annual compensation range for this role is listed below.\n\nAnnual Salary: \n$350,000 - $500,000 USD\n\n### Logistics\n\nMinimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience\nMinimum years of experience: Years of experience required will correlate with the internal job level requirements for the position\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.\nWe encourage you to apply even if you do not believe you meet every single qualification.\n\n### How we're different\n\nWe believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.\n\nCome work with us!\n\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.