{"id":26144,"url":"https://alion.io/job/dexmate-reinforcement-learning-engineer","title":"Reinforcement Learning Engineer","company":{"id":6958,"name":"Dexmate","domain":"dexmate.com","url":"https://alion.io/company/dexmate","size_band":"501-1000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"A","score":90,"open_postings":33,"ghost_share":0.091,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":169,"computed_at":"2026-10-17T05:46:00Z"}},"role":"AI/ML","role_family":"AI/ML","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":["Fremont, United States"],"countries":["US"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":120000,"max":300000,"currency":"USD","period":"year","gross":null,"usd_annual":300000},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Isaac Gym","optional":false},{"name":"Isaac Lab","optional":false},{"name":"JAX","optional":false},{"name":"Physical AI","optional":false},{"name":"PPO","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"TensorFlow","optional":false},{"name":"Isaac Sim","optional":true},{"name":"Sim-to-Real","optional":true}],"status":"live","first_seen_at":"2026-01-19T16:15:18Z","employer_posted_date":"2026-01-19","last_verified_at":"2026-10-17T10:17:08Z","board_verified":true,"closed_at":null,"days_open":270,"trust":{"level":"ok","repost_count":0,"flags":["company_stale"],"days_open":270},"description":"About Dexmate\nDexmate is building the foundation for physical AI - combining a new generation of robots with a universal Physical AI OS, making robots as easy to build and deploy as software. Today, robotics is fragmented, slow, and closed: most builders are forced to reinvent the same stack again and again, and most ideas never make it past the prototype stage. We exist to change that. Our mission is to democratize robotics by lowering the barrier to entry, delivering a plug-and-play platform for developers, researchers, and enterprises, and cultivating an open ecosystem that accelerates the evolution of physical AI.\nIf you want to help shape the next layer of human capability - and believe the future of robotics should be built together, not in isolation - we'd love to build it with you.\nThe Role\nWe're seeking Reinforcement Learning experts to develop and deploy cutting-edge RL algorithms that enhance our robots' capabilities.\nResponsibilities\nDesign and implement reinforcement learning algorithms for various robotics tasks\n\nDevelop and optimize RL training pipelines in both simulation and real-world environments\n\nCollaborate with robotics engineers to integrate RL models into production systems\n\nConduct experiments to evaluate and improve algorithm performance\n\nScale training infrastructure for efficient learning across multiple robots\n\nMinimum Qualifications\nStrong experience with reinforcement learning (PPO, SAC, TD3, DDPG, etc.)\n\nHands-on experience with robotics systems (simulation or real robots)\n\nProven track record applying RL to manipulation, locomotion, or navigation tasks\n\nProficiency in Python and deep learning frameworks (PyTorch, TensorFlow, JAX)\n\nStrong understanding of robot kinematics, dynamics, and control\n\nExperience with GPU-based simulation such as Isaac Gym, Isaac Lab, SAPIEN, etc.\n\nPreferred Qualifications\nExperience with distributed RL training systems\n\nExperience with sim-to-real transfer techniques\n\nPublications in robotics or RL conferences (CoRL, ICRA, RSS, NeurIPS, ICLR, ICML, etc.)","description_format":"text","description_chars":2048,"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":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Robotics AI","Humanoid Robots"],"lifecycle":[{"event":"open","at":"2026-01-19T16:15:18Z"}],"visa":[],"liveness":{"score":19,"band":"cold","label":"Long shot","p_open":1,"p_active":0.522,"p_room":0.36,"age_days":270,"expected_fill_days":169,"reasons":["conf:2","win:tail","crowd:"],"computed_at":"2026-10-17T05:46:00Z"},"pay":{"stated_usd_annual":300000,"is_top_pay":true},"html_url":"https://alion.io/job/dexmate-reinforcement-learning-engineer","json_url":"https://alion.io/job/dexmate-reinforcement-learning-engineer.json","meta":{"generated_at":"2026-10-17T10:49:42Z","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":14186,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-18T00:00:00Z"}},"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":6958},"rest":"https://alion.io/mcp/rest/get_company?id=6958"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fdexmate-reinforcement-learning-engineer"},{"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%2Fdexmate-reinforcement-learning-engineer"},{"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%2Fdexmate-reinforcement-learning-engineer"},{"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/dexmate-reinforcement-learning-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fdexmate-reinforcement-learning-engineer"}]}