{"schemaVersion":"jobsearcher.job.v1","id":"f55946e35735feafb3ec5e15","url":"https://jobsearcher.com/jobs/f55946e35735feafb3ec5e15","canonicalUrl":"https://jobsearcher.com/jobs/f55946e35735feafb3ec5e15","title":"Senior Inference & RL Systems Engineer","description":"Magic’s mission is to build safe AGI that accelerates humanity’s progress on the world’s most important problems. We believe the most promising path to safe AGI lies in automating research and code generation to improve models and solve alignment more reliably than humans can alone. Our approach combines frontier‑scale pre‑training, domain‑specific RL, ultra‑long context, and inference‑time compute to achieve this goal.\n\nAbout The Role\nAs a Software Engineer on the Inference & RL Systems team, you will design and operate the distributed systems that serve our models in production and power large‑scale post‑training workflows.\n\nThis role sits at the boundary between model execution and distributed infrastructure. You will work on systems that determine inference latency, throughput, stability, and the reliability of RL and post‑training training loops.\n\nMagic’s long‑context models introduce demanding execution constraints: KV‑cache scaling, memory pressure under long sequences, batching trade‑offs, long‑horizon trajectory rollouts, and sustained throughput under real‑world workloads. You will own the infrastructure that makes both production inference and large‑scale RL iteration fast and reliable.\n\nWhat you’ll work on\n\nDesign and scale high‑performance inference serving systems\n\nOptimize KV‑cache management, batching strategies, and scheduling\n\nImprove throughput and latency for long‑context workloads\n\nBuild and maintain distributed RL and post‑training infrastructure\n\nImprove reliability of rollout, evaluation, and reward pipelines\n\nAutomate fault detection and recovery for serving and RL systems\n\nProfile and eliminate performance bottlenecks across GPU, networking, and storage layers\n\nCollaborate with Kernels and Research to align execution systems with model architecture\n\nWhat we’re looking for\n\nStrong software engineering and distributed systems fundamentals\n\nExperience building or operating large‑scale inference or training systems\n\nDeep understanding of GPU execution constraints and memory trade‑offs\n\nExperience debugging performance issues in production ML systems\n\nAbility to reason about system‑level trade‑offs between latency, throughput, and cost\n\nTrack record of owning critical production infrastructure\n\nCompensation, Benefits, And Perks (US)\n\nAnnual salary range: $225K - $550K\n\nEquity is a significant part of total compensation, in addition to salary\n\n401(k) plan with 6% salary matching\n\nGenerous health, dental and vision insurance for you and your dependents\n\nUnlimited paid time off\n\nVisa sponsorship and relocation stipend to bring you to SF, if possible\n\nA small, fast‑paced, highly focused team\n\nOur culture\n\nIntegrity. Words and actions should be aligned\n\nHands‑on. At Magic, everyone is building\n\nTeamwork. We move as one team, not N individuals\n\nFocus. Safely deploy AGI. Everything else is noise\n\nQuality. Magic should feel like magic\n\n#J-18808-Ljbffr","company":"Magic","rawCompany":"magic","city":"Millbrae","state":"CA","isRemote":false,"isActive":false,"createdAt":"2026-06-20T04:16:01.980Z","occupations":[{"code":"15-1299.08","title":"Computer Systems Engineers/Architects","slug":"computer-systems-engineers-architects"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-1221.00","title":"Computer and Information Research Scientists","slug":"computer-and-information-research-scientists"}],"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":"Senior Inference & RL Systems Engineer","description":"Magic’s mission is to build safe AGI that accelerates humanity’s progress on the world’s most important problems. We believe the most promising path to safe AGI lies in automating research and code generation to improve models and solve alignment more reliably than humans can alone. Our approach combines frontier‑scale pre‑training, domain‑specific RL, ultra‑long context, and inference‑time compute to achieve this goal.\n\nAbout The Role\nAs a Software Engineer on the Inference & RL Systems team, you will design and operate the distributed systems that serve our models in production and power large‑scale post‑training workflows.\n\nThis role sits at the boundary between model execution and distributed infrastructure. You will work on systems that determine inference latency, throughput, stability, and the reliability of RL and post‑training training loops.\n\nMagic’s long‑context models introduce demanding execution constraints: KV‑cache scaling, memory pressure under long sequences, batching trade‑offs, long‑horizon trajectory rollouts, and sustained throughput under real‑world workloads. You will own the infrastructure that makes both production inference and large‑scale RL iteration fast and reliable.\n\nWhat you’ll work on\n\nDesign and scale high‑performance inference serving systems\n\nOptimize KV‑cache management, batching strategies, and scheduling\n\nImprove throughput and latency for long‑context workloads\n\nBuild and maintain distributed RL and post‑training infrastructure\n\nImprove reliability of rollout, evaluation, and reward pipelines\n\nAutomate fault detection and recovery for serving and RL systems\n\nProfile and eliminate performance bottlenecks across GPU, networking, and storage layers\n\nCollaborate with Kernels and Research to align execution systems with model architecture\n\nWhat we’re looking for\n\nStrong software engineering and distributed systems fundamentals\n\nExperience building or operating large‑scale inference or training systems\n\nDeep understanding of GPU execution constraints and memory trade‑offs\n\nExperience debugging performance issues in production ML systems\n\nAbility to reason about system‑level trade‑offs between latency, throughput, and cost\n\nTrack record of owning critical production infrastructure\n\nCompensation, Benefits, And Perks (US)\n\nAnnual salary range: $225K - $550K\n\nEquity is a significant part of total compensation, in addition to salary\n\n401(k) plan with 6% salary matching\n\nGenerous health, dental and vision insurance for you and your dependents\n\nUnlimited paid time off\n\nVisa sponsorship and relocation stipend to bring you to SF, if possible\n\nA small, fast‑paced, highly focused team\n\nOur culture\n\nIntegrity. Words and actions should be aligned\n\nHands‑on. At Magic, everyone is building\n\nTeamwork. We move as one team, not N individuals\n\nFocus. Safely deploy AGI. Everything else is noise\n\nQuality. Magic should feel like magic\n\n#J-18808-Ljbffr","datePosted":"2026-06-20T04:16:01.980Z","dateModified":"2026-06-20T04:16:01.980Z","hiringOrganization":{"@type":"Organization","name":"Magic","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Millbrae","addressRegion":"CA","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"f55946e35735feafb3ec5e15"},"url":"https://jobsearcher.com/jobs/f55946e35735feafb3ec5e15"}}