{"id":69764,"url":"https://alion.io/job/thinking-machines-lab-research-rl-scaling","title":"Research, RL Scaling","company":{"id":14382,"name":"Thinking Machines Lab","domain":"thinkingmachines.ai","url":"https://alion.io/company/thinking-machines-lab","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":null},"role":"Web3","role_family":"Web3","seniority":null,"employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["San Francisco, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":350000,"max":475000,"currency":"USD","period":"year","gross":null,"usd_annual":475000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Clarity","optional":false},{"name":"JAX","optional":false},{"name":"KV Cache","optional":false},{"name":"Machine Learning","optional":false},{"name":"Mixture of Experts","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Quantization","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Speculative Decoding","optional":false},{"name":"TensorFlow","optional":false},{"name":"AI Agents","optional":true},{"name":"LLM","optional":true},{"name":"SGLang","optional":true},{"name":"vLLM","optional":true}],"status":"live","first_seen_at":"2026-08-21T19:15:28Z","employer_posted_date":"2026-08-21","last_verified_at":"2026-10-20T19:22:50Z","board_verified":true,"closed_at":null,"days_open":60,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":60},"description":"About Thinking Machines\nThe mission of Thinking Machines is to build AI that extends human will and judgment. We are training frontier models with Inkling, developing Tinker to let people make models their own, and crafting interfaces that broaden human-AI communication. We believe the future worth building is human, and we're hiring people who want to build it.\nAbout the Role\nOur team scales reinforcement learning for frontier models. Progress in RL is increasingly set by how well it scales: more rollouts, larger models, and training loops that keep large fleets of accelerators doing useful work. We are particularly interested in people working on high-training-compute, long-horizon RL. We believe the biggest gains come from designing the training recipe and the infrastructure together rather than separately, and we are hiring a researcher who wants to own that boundary.\nA center of gravity for this role is asynchronous RL. Decoupling generation from training changes both the systems design and the learning problem, and doing it well requires a deep understanding of async RL algorithms, design choices, and trade-offs on both the ML and the systems sides. We expect much of the headroom in RL scaling to come from here.\nBecause generation dominates the cost of RL at scale, good knowledge of inference systems, low-precision numerics, and quantization is recommended: you should be able to reason quantitatively about rollout throughput and cost (batching, KV cache, MoE serving, speculative decoding) and about how inference constraints shape training design.\nThis is a research role with full-stack ownership, from the algorithms to the parallelism plan to the health of the run.\nWhat You’ll Do\nCo-design the RL recipe and the systems that run it: make recipe-level choices jointly with systems-level ones and validate them at frontier scale.\n\nAdvance asynchronous RL algorithms.\n\nImprove the efficiency of rollout generation and its integration with training, treating inference as a first-class part of the RL loop.\n\nRun frontier-scale RL end to end: bring up new models and training setups, keep large runs stable and healthy.\n\nJointly optimize the compute and training efficiency of RL: accelerator utilization, memory, communication, and low-precision numerics.\n\nDo careful empirical science: ablations and scaling studies backed by instrumentation you can trust, written up clearly.\n\nSkills and Qualifications\nMinimum qualifications:\nProficiency in Python and familiarity with at least one deep learning framework (e.g., PyTorch, TensorFlow, or JAX). Comfortable with debugging distributed training and writing code that scales.\n\nBachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding.\n\nClarity in communication, an ability to explain complex technical concepts in writing.\n\nStrong research judgment: clean ablations, honest baselines, and clear technical writing.\n\nPreferred qualifications - we encourage you to apply if you meet some but not all of these:\nPhD in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding; or, equivalent industry research experience.\n\nStrong grounding in RL for large language models, such as modern policy optimization methods and their behavior at scale.\n\nDeep understanding of asynchronous RL: the algorithms, design choices, and trade-offs, on both the ML and the systems sides.\n\nExperience training large models across many accelerators, with comfort inside the distributed stack (parallelism strategies, memory, communication).\n\nGood working knowledge of inference systems: able to reason quantitatively about rollout generation throughput and cost.\n\nExperience building or operating decoupled generation/training RL systems at scale.\n\nExperience with RL on verifiable and agentic tasks, including multi-turn environments.\n\nExperience with RL training stability techniques for large runs.\n\nFamiliarity with low-precision training and inference: numerics, quantization, and their implications for RL.\n\nHands-on work with LLM serving stacks (e.g., SGLang, vLLM, TokenSpeed, or custom engines).\n\nExperience with scaling studies for large models.\n\nContributions to open-source training or inference frameworks.\n\nLogistics\nLocation: This role is based in San Francisco, California.\n\nCompensation: Depending on background, skills and experience, the expected annual salary range for this position is $350,000 - $475,000 USD.\n\nVisa sponsorship: We sponsor visas. While we can't guarantee success for every candidate or role, if you're the right fit, we're committed to working through the visa process together.\n\nBenefits: Thinking Machines offers generous health, dental, and vision benefits, unlimited PTO, paid parental leave, and relocation support as needed.\n\nAs set forth in Thinking Machines' Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under any applicable law.","description_format":"text","description_chars":5081,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"phd","optional":true},"security_clearance":false,"languages":[]},"benefits":["Parental leave","Unlimited PTO"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":true,"industries":["Multimodal AI","Foundation Models","AI Research Labs","AI Development Tools"],"lifecycle":[{"event":"open","at":"2026-08-21T19:15:28Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 30","filings_12m":30,"filings_prev_12m":8,"green_card_filings_12m":0,"median_offered_wage_usd":192500,"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":7}],"liveness":{"score":16,"band":"cold","label":"Long shot","p_open":1,"p_active":0.461,"p_room":0.35,"age_days":59,"expected_fill_days":29,"reasons":["conf:3","velocity","win:tail"],"computed_at":"2026-10-20T05:45:00Z"},"pay":{"stated_usd_annual":475000,"is_top_pay":true},"html_url":"https://alion.io/job/thinking-machines-lab-research-rl-scaling","json_url":"https://alion.io/job/thinking-machines-lab-research-rl-scaling.json","meta":{"generated_at":"2026-10-20T21:11:04Z","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":24647,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-21T00:00:00Z"}},"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":14382},"rest":"https://alion.io/mcp/rest/get_company?id=14382"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fthinking-machines-lab-research-rl-scaling"},{"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%2Fthinking-machines-lab-research-rl-scaling"},{"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%2Fthinking-machines-lab-research-rl-scaling"},{"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/thinking-machines-lab-research-rl-scaling\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fthinking-machines-lab-research-rl-scaling"}]}