{"id":91902,"url":"https://alion.io/job/humanoid-reinforcement-learning-engineer-manipulation","title":"Reinforcement Learning Engineer - Manipulation","company":{"id":35230,"name":"Humanoid","domain":"thehumanoid.ai","url":"https://alion.io/company/thehumanoid","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":77,"open_postings":11,"ghost_share":0,"stale_share":0.909,"repost_share":0,"time_to_fill_p50_days":56,"computed_at":"2026-10-16T05:45:00Z"}},"role":"Robotics","role_family":"Robotics","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["London, United Kingdom"],"countries":["GB"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":80000,"max_usd":180000,"period":"year","method":"global_role_cell_scaled_by_country","sample_n":126},"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":true,"technologies":[{"name":"JAX","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Isaac Sim","optional":true},{"name":"MuJoCo","optional":true},{"name":"OpenVLA","optional":true},{"name":"Ray","optional":true}],"status":"live","first_seen_at":"2026-07-16T10:46:40Z","employer_posted_date":"2026-07-16","last_verified_at":"2026-10-16T17:29:53Z","board_verified":true,"closed_at":null,"days_open":92,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":92},"description":"Here at Humanoid, we believe in a future where robots amplify human potential. That’s why we’ve set out on a mission to build the world’s most capable, commercially-scalable, and safe humanoid robots. We’re bringing that mission to life with HMND-01 - our rapidly developed humanoid platform being deployed in real industrial environments - and we’re growing the team to take it even further.\nAbout the Role\nWe're hiring a Reinforcement Learning Engineer to join our Autonomy team based in London. In this role you will leverage reinforcement learning in both simulation and physical reality to build highly performant and robust manipulation policies.\nWhat You'll Do\nTrain language-vision conditioned manipulation policies via reinforcement learning (RL) in simulation and in the real world.\n\nConstruct challenging and diverse suites of manipulation tasks in simulation.\n\nPartner with teleoperations to collect trajectories in simulation for behavior cloning.\n\nPartner with testing and operations to establish real-world RL training pipelines.\n\nExperiment with various ways of bringing policies trained in simulation to the real world.\n\nWhat We're Looking For\n3+ years building deep-learning systems (industry or research) with shipped models or published artifacts to show for it.\n\nHands-on with at least one of: LLMs, VLMs, or image/video generative models - architecture, training, and inference.\n\nExperience solving real problems using reinforcement learning with deep neural networks in any domain.\n\nStrong Python + PyTorch/JAX; you can profile, debug numerics, and write maintainable research code.\n\nYou are self-driven, pro-active, communicate efficiently, document experiments clearly and communicate trade-offs crisply.\n\nNice to have\nExperience with simulators for robotics (Isaac Sim, MuJoCo etc.)\n\nExperience in RL for robotics.\n\nExperience building infrastructure for large-scale RL (e.g. using ray).\n\nPublications at ICLR/ICML/NeurIPS or equivalent open-source contributions.\n\nFamiliarity with OpenVLA, Physical Intelligence (π) models, or similar open VLA frameworks.\n\nWhat We Offer\nCompetitive equity: stock options with meaningful upside as we scale.\n\n30+ paid days off, including 23 days of annual leave, all UK bank holidays, and additional company closure days (including Christmas-New Year shutdown).\n\nPrivate healthcare, including virtual and in-person care.\n\nPension scheme with 8% total contribution (5% employee, 3% employer) on full earnings.\n\nFree daily breakfast, catered lunch, and snacks in-office.\n\nWork at the frontier - collaborate daily with world-class engineers, researchers, and product experts building the next generation of AI and humanoid robotics.\n\nReal ownership - direct access to founding leadership, meaningful input on product direction, and the ability to drive key initiatives from day one.","description_format":"text","description_chars":2839,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":["Annual leave","Equity","Stock options"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Robotics AI","Logistics & Warehouse Robotics","Industrial Robotics","Humanoid Robots"],"lifecycle":[{"event":"open","at":"2026-07-16T10:46:40Z"}],"visa":[],"liveness":{"score":17,"band":"cold","label":"Long shot","p_open":1,"p_active":0.463,"p_room":0.36,"age_days":91,"expected_fill_days":56,"reasons":["conf:1","stale_co","velocity","win:tail","crowd:brand"],"computed_at":"2026-10-16T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/humanoid-reinforcement-learning-engineer-manipulation","json_url":"https://alion.io/job/humanoid-reinforcement-learning-engineer-manipulation.json","meta":{"generated_at":"2026-10-16T18:04:02Z","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":2979,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-17T00:00:00Z"}},"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":35230},"rest":"https://alion.io/mcp/rest/get_company?id=35230"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fhumanoid-reinforcement-learning-engineer-manipulation"},{"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%2Fhumanoid-reinforcement-learning-engineer-manipulation"},{"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%2Fhumanoid-reinforcement-learning-engineer-manipulation"},{"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/humanoid-reinforcement-learning-engineer-manipulation\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fhumanoid-reinforcement-learning-engineer-manipulation"}]}