{"id":35017,"url":"https://alion.io/job/luma-ai-research-scientist-engineer-reinforcement-learning-infrastructure","title":"Research Scientist / Engineer – Reinforcement Learning Infrastructure","company":{"id":247,"name":"Luma AI","domain":"lumalabs.ai","url":"https://alion.io/company/luma-ai","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":null,"employment_type":"full_time","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Redwood City, United States","New York, United States","Seattle, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":195000,"max":395000,"currency":"USD","period":"year","gross":null,"usd_annual":395000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Computer Use","optional":false},{"name":"FSDP","optional":false},{"name":"Function Calling","optional":false},{"name":"GRPO","optional":false},{"name":"LLM","optional":false},{"name":"LLM Evaluation","optional":false},{"name":"MPI","optional":false},{"name":"Multimodal AI","optional":false},{"name":"NCCL","optional":false},{"name":"Post-training","optional":false},{"name":"PPO","optional":false},{"name":"PyTorch","optional":false},{"name":"Ray","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"RLHF","optional":false},{"name":"SGLang","optional":false},{"name":"TRL","optional":false},{"name":"vLLM","optional":false},{"name":"C","optional":true},{"name":"Kubernetes","optional":true},{"name":"Transformers","optional":true}],"status":"live","first_seen_at":"2026-07-24T21:55:45Z","employer_posted_date":"2026-07-24","last_verified_at":"2026-10-26T12:07:01Z","board_verified":true,"closed_at":null,"days_open":93,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":93},"description":"You'll build the systems that make reinforcement learning work at frontier scale - coupling policy optimization with large fleets of inference workers, agentic environments, and the reward and verification systems that turn model behavior into learning signal. RL is how Luma's models go from capable to useful.\nRL at scale is a full-loop systems problem: training, rollout generation, environment execution, and reward computation running concurrently across thousands of GPUs, all needing to stay fast, stable, and correct together. It fits someone who has lived this - post-trained LLMs with RL, built environments and verifiers, and debugged asynchronous rollout pipelines at scale. If you haven't operated RL at real scale, this will be deep water.\nWhat You'll Own\nDesign, build, and scale distributed RL post-training systems, orchestrating trainer, rollout, environment, and reward workloads across thousands of GPUs.\n\nBuild high-throughput rollout generation, integrating inference engines (vLLM, SGLang), weight synchronization, and asynchronous/off-policy schemes.\n\nDesign RL environments for agentic, multi-step tasks - sandboxed code execution, tool use, computer use, multimodal interaction - reproducible and scalable to millions of episodes.\n\nBuild reward infrastructure: verifiable/programmatic rewards, reward-model serving, LLM-as-judge pipelines, and defenses against reward hacking.\n\nDevelop the evaluation, monitoring, and debugging tooling that keeps large RL runs stable.\n\nAdvance training efficiency and stability, and turn new post-training ideas into production runs with researchers.\n\nFirst 90 Days\nOne way the first 90 could unfold.\nDays 1-30 - Immerse & Diagnose: Learn the current RL stack and where throughput, stability, or correctness break.\n\nDays 30-60 - Ship & Validate: Improve a piece of the loop (rollout throughput, reward infra, or an environment) and prove it on a real run.\n\nDays 60-90 - Scale & Systemize: Harden the full loop across thousands of GPUs and asynchronous architectures.\n\nWhat You Bring\nHands-on experience post-training LLMs with RL (PPO/GRPO-family, RLHF, RLVR) at meaningful scale.\n\nExtensive distributed PyTorch training and parallelism (FSDP, Tensor/Pipeline/Expert Parallel) for foundation models.\n\nExperience building RL environments, reward functions, verifiers, or evaluation harnesses for LLM agents, including sandboxed execution and multi-turn tool use.\n\nDeep familiarity with RL post-training frameworks (veRL, OpenRLHF, TRL, Ray orchestration) and rollout inference engines (vLLM, SGLang).\n\nStrong understanding of GPU clusters, networking, and communication libraries (NCCL, MPI) under mixed training and inference workloads.\n\nNice to Have\nRunning RL training across 100+ GPUs, including asynchronous or disaggregated trainer/rollout architectures.\n\nContainerization and orchestration (Kubernetes, Ray) for large environment fleets and sandboxed workloads.\n\nResearch contributions in RL for LLMs, or open-source contributions to RL training frameworks.\n\nAbout Luma: Luma's mission is to build unified general intelligence that can generate, understand, and operate in the physical world. We believe multimodality is critical for intelligence - the next step beyond language models comes from vision. Luma is an equal opportunity employer.","description_format":"text","description_chars":3309,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Generative 3D","Generative Image","Generative Video"],"lifecycle":[{"event":"open","at":"2026-07-24T21:55:45Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 37","filings_12m":37,"filings_prev_12m":9,"green_card_filings_12m":0,"median_offered_wage_usd":183446,"route":null,"cap_exempt":false,"checked_at":"2026-10-15T11:24:14+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)"],"filings_for_role_12m":0}],"liveness":{"score":23,"band":"cold","label":"Long shot","p_open":1,"p_active":0.629,"p_room":0.36,"age_days":93,"expected_fill_days":57,"reasons":["conf:2","wave","velocity","win:tail","crowd:"],"computed_at":"2026-10-26T05:57:25Z"},"pay":{"stated_usd_annual":395000,"is_top_pay":true},"html_url":"https://alion.io/job/luma-ai-research-scientist-engineer-reinforcement-learning-infrastructure","json_url":"https://alion.io/job/luma-ai-research-scientist-engineer-reinforcement-learning-infrastructure.json","meta":{"generated_at":"2026-10-26T13:00:42Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":18020,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-27T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":247},"rest":"https://alion.io/mcp/rest/get_company?id=247"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fluma-ai-research-scientist-engineer-reinforcement-learning-infrastructure"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fluma-ai-research-scientist-engineer-reinforcement-learning-infrastructure"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fluma-ai-research-scientist-engineer-reinforcement-learning-infrastructure"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/luma-ai-research-scientist-engineer-reinforcement-learning-infrastructure\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fluma-ai-research-scientist-engineer-reinforcement-learning-infrastructure"}]}