{"schemaVersion":"jobsearcher.job.v1","id":"49c1a3fc09450cdcd33716b2","url":"https://jobsearcher.com/jobs/49c1a3fc09450cdcd33716b2","canonicalUrl":"https://jobsearcher.com/jobs/49c1a3fc09450cdcd33716b2","title":"Research Engineer, Post-Training","description":"General Analysis is a frontier security lab. We protect the world as AI systems grow more capable and more dangerous in the wrong hands. We build high-fidelity research infrastructure that evaluates and strengthens frontier models on critical cyberdefense tasks, and we bring that research directly to enterprises — securing the AI systems they deploy through adversarial testing and runtime protection.\nAbout the role As a Research Engineer, you will be responsible for post-training models for adversarial capabilities using reinforcement learning.\nYou will work on the entire training pipeline from data generation and environment design to evaluations.\nYou will tackle engineering challenges involving distributed systems, innovate new methods for data-constrained and low signal-to-noise environments, and make algorithmic improvements for applying trained models for adversarial simulations.\nYou may be a good fit if You are comfortable with PyTorch, RL infrastructure, post-training infrastructure, or tools such as Tinker and verl.\nYou have academic and/or industry experience with reinforcement learning or machine learning research, or are eager to learn.\nYou have publications in top-tier venues such as NeurIPS, ICML, ICLR, CVPR, ACL, or similar.\nYou have security experience, or are excited to build it here.\nYou have a high level of agency, strong technical acumen, and clarity of thought.\nYou'll thrive here if You are excited about applying novel research and new technology to real-world problems.\nYou are excited to learn new domains and build deep context in AI security.\nYou are results-oriented and can balance deep exploration with practical implementation.\nYou proactively step outside defined boundaries to support the team's mission and unblock others.\n\n#J-18808-Ljbffr","company":"General Analysis","rawCompany":"general analysis","city":"Millbrae","state":"CA","isRemote":false,"isActive":true,"createdAt":"2026-09-09T03:20:54.418Z","occupations":[{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"},{"code":"15-1299.05","title":"Information Security Engineers","slug":"information-security-engineers"},{"code":"15-1212.00","title":"Information Security Analysts","slug":"information-security-analysts"}],"industries":[{"code":"541715","title":"Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)","slug":"research-and-development-in-the-physical-engineering-and-life-sciences-except-nanotechnology-and-biotechnology"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"541690","title":"Other Scientific and Technical Consulting Services","slug":"other-scientific-and-technical-consulting-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Research Engineer, Post-Training","description":"General Analysis is a frontier security lab. We protect the world as AI systems grow more capable and more dangerous in the wrong hands. We build high-fidelity research infrastructure that evaluates and strengthens frontier models on critical cyberdefense tasks, and we bring that research directly to enterprises — securing the AI systems they deploy through adversarial testing and runtime protection.\nAbout the role As a Research Engineer, you will be responsible for post-training models for adversarial capabilities using reinforcement learning.\nYou will work on the entire training pipeline from data generation and environment design to evaluations.\nYou will tackle engineering challenges involving distributed systems, innovate new methods for data-constrained and low signal-to-noise environments, and make algorithmic improvements for applying trained models for adversarial simulations.\nYou may be a good fit if You are comfortable with PyTorch, RL infrastructure, post-training infrastructure, or tools such as Tinker and verl.\nYou have academic and/or industry experience with reinforcement learning or machine learning research, or are eager to learn.\nYou have publications in top-tier venues such as NeurIPS, ICML, ICLR, CVPR, ACL, or similar.\nYou have security experience, or are excited to build it here.\nYou have a high level of agency, strong technical acumen, and clarity of thought.\nYou'll thrive here if You are excited about applying novel research and new technology to real-world problems.\nYou are excited to learn new domains and build deep context in AI security.\nYou are results-oriented and can balance deep exploration with practical implementation.\nYou proactively step outside defined boundaries to support the team's mission and unblock others.\n\n#J-18808-Ljbffr","datePosted":"2026-09-09T03:20:54.418Z","dateModified":"2026-09-09T03:20:54.418Z","hiringOrganization":{"@type":"Organization","name":"General Analysis","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"49c1a3fc09450cdcd33716b2"},"url":"https://jobsearcher.com/jobs/49c1a3fc09450cdcd33716b2"}}