{"id":48786,"url":"https://alion.io/job/centific-applied-reinforcement-learning-engineer","title":"Applied Reinforcement Learning Engineer","company":{"id":9945,"name":"Centific","domain":"centific.com","url":"https://alion.io/company/centific","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"services","is_intermediary":false,"listed_via":null,"ats_vendor":"Workday","truth_index":{"grade":"C","score":62,"open_postings":95,"ghost_share":0.632,"stale_share":0,"repost_share":0,"time_to_fill_p50_days":29,"computed_at":"2026-10-17T05:46:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"middle","employment_type":"full_time","work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"board_field","remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["United States"],"countries":["US"],"hiring_countries":["US"],"hiring_countries_total":1,"salary":{"min":150000,"max":300000,"currency":"USD","period":"year","gross":null,"usd_annual":300000},"salary_estimate":null,"experience_years_min":3,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Digital Twin","optional":false},{"name":"DPO","optional":false},{"name":"Fine-tuning","optional":false},{"name":"Function Calling","optional":false},{"name":"GRPO","optional":false},{"name":"Gymnasium","optional":false},{"name":"LLM","optional":false},{"name":"OpenAI","optional":false},{"name":"Post-training","optional":false},{"name":"PPO","optional":false},{"name":"RAG","optional":false},{"name":"Reinforcement Learning","optional":false},{"name":"Reward Modeling","optional":false},{"name":"RLHF","optional":false},{"name":"Sim-to-Real","optional":false},{"name":"Tool Use","optional":false},{"name":"World Models","optional":false},{"name":"JAX","optional":true},{"name":"Python","optional":true},{"name":"PyTorch","optional":true},{"name":"Ray","optional":true},{"name":"RLlib","optional":true},{"name":"Stable-Baselines3","optional":true},{"name":"Synthetic Data","optional":true},{"name":"TensorFlow","optional":true},{"name":"Transformers","optional":true},{"name":"TRL","optional":true}],"status":"live","first_seen_at":"2026-07-08T00:00:00Z","employer_posted_date":"2026-07-08","last_verified_at":"2026-10-17T07:14:26Z","board_verified":true,"closed_at":null,"days_open":101,"trust":{"level":"ghost","repost_count":0,"flags":["stale","company_stale"],"days_open":101},"description":"About Centific\nCentific is a frontier AI data foundry that curates diverse, high-quality data, using our purpose-built technology platforms to empower the Magnificent Seven and our enterprise clients with safe, scalable AI deployment. Our team includes more than 150 PhDs and data scientists, along with more than 4,000 AI practitioners and engineers. We harness the power of an integrated solution ecosystem-comprising industry-leading partnerships and 1.8 million vertical domain experts in more than 230 markets-to create contextual, multilingual, pre-trained datasets; fine-tuned, industry-specific LLMs; and RAG pipelines supported by vector databases. Our zero-distance innovation™ solutions for GenAI can reduce GenAI costs by up to 80% and bring solutions to market 50% faster.\nOur mission is to bridge the gap between AI creators and industry leaders by bringing best practices in GenAI to unicorn innovators and enterprise customers. We aim to help these organizations unlock significant business value by deploying GenAI at scale, helping to ensure they stay at the forefront of technological advancement and maintain a competitive edge in their respective markets.\nAbout Job\nRole: Applied Reinforcement Learning Engineer\nLocation: Palo Alto, CA or Seattle, WA (Hybrid/Remote)\nAbout the Team\nCentific AI Research advances foundational AI models and applications through reinforcement learning, alignment, and human-centered intelligence. Our mission is to transform data, signals, and human insight into next-generation intelligent systems that redefine enterprise intelligence.\nWe're building a governed RL environment platform that enables enterprises to safely iterate and improve AI agent workflows through simulation-based learning, bridging human-labeled signal creation with automated RL training for high-stakes operations.\nRole Overview\nAs an Applied RL Engineer, you will design and build RL environments that simulate complex enterprise workflows and train intelligent agents within them. You'll work at the intersection of RL research and production systems, translating customer requirements into bespoke simulation environments and post-training pipelines that deliver measurable improvements to AI agent performance.\nThis role requires deep expertise in both classical RL methodologies and modern LLM-based agent architectures. You'll shape our product direction and help make RL accessible to enterprise customers who need safe, compliant ways to improve their AI systems.\nCore RL Competencies\nFoundational RL\nMDPs & value methods: State/action spaces, Q-learning, DQN, Double DQN, Dueling DQN\nPolicy gradient methods: REINFORCE, Actor-Critic, A2C/A3C, variance reduction\nAdvanced optimization: PPO, TRPO, SAC, trust regions, entropy regularization\nTD learning: TD(0), TD(λ), eligibility traces, bootstrapping methods\nLLM Alignment & Post-Training\nRLHF pipelines: Reward model training, preference learning, human feedback integration\nDirect optimization: DPO, IPO, KTO, offline preference optimization\nGroup-based methods: GRPO, RLOO, sample-efficient policy improvement\nReward modeling: Bradley-Terry models, reward hacking mitigation, KL constraints\nEnvironment Design\nGymnasium/OpenAI Gym: Custom environments, observation/action spaces, wrapper patterns\nReward engineering: Sparse vs. dense rewards, potential-based shaping, intrinsic motivation\nVerifier design: Programmatic reward functions, outcome verification, ground-truth evaluation\nSimulation: Sim-to-real transfer, domain randomization, multi-agent dynamics\nAdvanced Techniques\nOffline RL: CQL, BCQ, IQL for learning from fixed datasets without environment interaction\nModel-based RL: World models, Dreamer, MuZero, learned dynamics\nHierarchical RL: Options framework, goal-conditioned policies, temporal abstraction\nImitation & exploration: Behavioral cloning, GAIL, curiosity-driven exploration, UCB\nKey Responsibilities\nDesign and build custom RL environments (digital twins) simulating enterprise workflows: document processing, compliance, onboarding, support automation\nPost-train LLM-based agents on domain-specific tasks using PPO, GRPO, DPO, and RLHF\nBuild end-to-end pipelines converting human-labeled traces into RL training data\nArchitect multi-step reasoning agents with tool-calling and closed learning loops\nDesign reward functions, verifiers, and validation frameworks for pre-deployment testing\nTranslate cutting-edge RL research into production systems; contribute to publications\nRequired Qualifications\nDeep RL expertise: 3+ years hands-on experience with environment design, reward engineering, policy optimization\nLLM post-training: Experience fine-tuning LLMs using RLHF, DPO, PPO, or similar\nProduction skills: Software engineering beyond research with scalable pipelines and training infrastructure\nAgentic AI: Experience with LLM-based agents, tool use, multi-step reasoning\nTechnical stack: Strong Python; Gymnasium, RLlib, Stable Baselines; PyTorch/JAX/TensorFlow\nEducation: MS/PhD in CS, ML, or related field (or equivalent experience)\nPreferred Qualifications\nPublications at NeurIPS, ICML, ICLR, ACL, or similar venues\nEnterprise workflow experience in healthcare, finance, logistics, or compliance\nOpen-source contributions to CleanRL, TRL, veRL, or agent frameworks\nExperience with world models, synthetic data generation, and simulation\nDistributed training and large-scale RL experimentation\nWhy Join Centific\nLead the frontier: Shape a new discipline at the intersection of RL, simulation, and enterprise AI\nShip your science: See your research power real systems across healthcare, finance, and safety\nCollaborate with leaders: Work alongside NVIDIA, Microsoft, and the global AI community\nBuild what matters: Create governed, compliant AI systems enterprises can trust.\nSalary: $150K - $300K Annually\nCentific is an equal-opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, national origin, ancestry, citizenship status, age, mental or physical disability, medical condition, sex (including pregnancy), gender identity or expression, sexual orientation, marital status, familial status, veteran status, or any other characteristic protected by applicable law. We consider qualified applicants regardless of criminal histories, consistent with legal requirements.","description_format":"text","description_chars":6369,"description_truncated":false,"requirements":{"experience_years_min":3,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"United States","iso":"US","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["Translation Services","AI Consulting & Integration","AI Training Data & Annotation","AI Evaluation & Observability"],"lifecycle":[{"event":"open","at":"2026-07-08T00:00:00Z"}],"visa":[],"liveness":{"score":8,"band":"cold","label":"Long shot","p_open":1,"p_active":0.274,"p_room":0.28,"age_days":101,"expected_fill_days":29,"reasons":["conf:38","stale_co","velocity","ghost","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/centific-applied-reinforcement-learning-engineer","json_url":"https://alion.io/job/centific-applied-reinforcement-learning-engineer.json","meta":{"generated_at":"2026-10-17T18:10:04Z","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":781,"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":9945},"rest":"https://alion.io/mcp/rest/get_company?id=9945"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fcentific-applied-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%2Fcentific-applied-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%2Fcentific-applied-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/centific-applied-reinforcement-learning-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fcentific-applied-reinforcement-learning-engineer"}]}