{"id":2286445,"url":"https://alion.io/job/deeproute-research-scientist-reinforcement-learning","title":"Research Scientist, Reinforcement Learning","company":{"id":32446,"name":"DeepRoute.ai","domain":"deeproute.ai","url":"https://alion.io/company/deeproute","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Workable","truth_index":{"grade":"B","score":75,"open_postings":4,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":null,"computed_at":"2026-10-12T06:55:09Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":null,"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":null,"salary_estimate":{"min_usd":149000,"max_usd":326000,"period":"year","method":"role_country_seniority_unknown","sample_n":3786},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"C++","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"DPO","optional":false},{"name":"Fine-tuning","optional":false},{"name":"GRPO","optional":false},{"name":"LLM","optional":false},{"name":"PPO","optional":false},{"name":"Python","optional":false},{"name":"PyTorch","optional":false},{"name":"PyTorch C++","optional":false},{"name":"Quantization","optional":false},{"name":"Ray","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reward Modeling","optional":false},{"name":"RLHF","optional":false},{"name":"Sim-to-Real","optional":false},{"name":"Vision-Language-Action","optional":false},{"name":"VLM","optional":false}],"status":"live","first_seen_at":"2026-06-06T00:00:00Z","employer_posted_date":"2026-06-06","last_verified_at":"2026-10-12T14:11:38Z","board_verified":true,"closed_at":null,"days_open":128,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":128},"description":"We are building next-generation end-to-end autonomous driving systems powered by reinforcement learning.\nYou will work on applying RL in closed-loop, safety-critical environments, leveraging large-scale simulation and real-world driving data to improve safety, comfort, and robustness.\n Train and deploy RL policies in closed-loop driving environments \n Scale RL training using massively parallel simulation systems \n Design and optimize reward functions for complex driving behaviors \n Improve sim-to-real transfer for real-world robustness \n Collaborate with cross-functional teams to integrate models into production systems \nRequirements\nCore Technical Skills\nProficiency in modern RL algorithms: DQN, PPO, SAC, TD3, etc.\nProficiency in modern RLHF algorithms: PPO, DPO, GRPO, etc.\nHands-on experience training reward models and finetuning LLM/VLM/VLA\nKnowledge of distributed RL training at scale\nProficiency with massively parallel simulation environments\nKnowledge of sim-to-real transfer techniques and domain randomization\nProficiency in Python, comfortable with C++\nProficiency in deep learning frameworks such as PyTorch\nExperience with distributed training frameworks (Ray, Horovod, etc.)\nKnowledge of model optimization (quantization, pruning) and CUDA is a plus\nKnowledge of traffic rules, driving behavior modeling\nPreferred Qualifications\nPublications in top-tier venues (ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV, ICRA, IROS, etc.)\nOpen-source contributions to RL libraries or autonomous driving projects\nPrevious experience with LLM fine-tuning using RLHF\nKnowledge of safe RL, interpretable AI, or robustness techniques\nFamiliarity with autonomous vehicle regulations and safety standards","description_format":"text","description_chars":1703,"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":["Autonomous Driving","Computer Vision"],"lifecycle":[{"event":"open","at":"2026-10-11T14:08:11Z"}],"visa":[],"liveness":{"score":5,"band":"cold","label":"Long shot","p_open":1,"p_active":0.17,"p_room":0.28,"age_days":128,"expected_fill_days":20,"reasons":["conf:1","win:tail","crowd:"],"computed_at":"2026-10-12T06:55:09Z"},"pay":null,"html_url":"https://alion.io/job/deeproute-research-scientist-reinforcement-learning","json_url":"https://alion.io/job/deeproute-research-scientist-reinforcement-learning.json","meta":{"generated_at":"2026-10-12T15:34:19Z","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":"assistant_verified","counted_by":"address","units_charged":1,"used_today":3310,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-13T00:00:00Z"}},"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":32446},"rest":"https://alion.io/mcp/rest/get_company?id=32446"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fdeeproute-research-scientist-reinforcement-learning"},{"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%2Fdeeproute-research-scientist-reinforcement-learning"},{"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%2Fdeeproute-research-scientist-reinforcement-learning"},{"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/deeproute-research-scientist-reinforcement-learning\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fdeeproute-research-scientist-reinforcement-learning"}]}