Senior Staff Research Scientist - RL

Centific is a frontier AI data foundry that curates diverse, high-quality data using purpose-built technology platforms, empowering the Magnificent Seven and enterprise clients with safe, scalable AI. Our team includes 150+ PhDs, 4,000+ AI practitioners, and 2M+ vertical domain experts across 230+ markets. In this role you will design simulation environments that mirror real enterprise workflows and post-train LLM agents inside them. Your environments, reward functions, and verifiers become the training ground for production agents handling document processing, compliance, customer operations, and multi-step reasoning across regulated industries. This role sits at the intersection of LLM post-training research and production engineering. You will translate customer workflows into bespoke environments, design reward signals that hold up under optimization pressure, and ship pipelines that turn human-labeled traces into measurable agent improvements. Title: Senior Staff Research Scientist – RL Job Description What You'll Do Design simulation environments and digital twins for enterprise workflows Post-train LLM agents using RLHF, DPO, GRPO, PPO, and emerging methods Build pipelines that convert human-labeled traces and verifiable signals into training data Architect multi-turn, tool-using agents with closed learning loops Design reward functions and verifiers that resist reward hacking and reflect real task outcomes Set the technical bar across the team — architecture, code review, engineering standards Mentor researchers and engineers; drive technical direction through influence Translate research into production; contribute to publications Experience & Education 7+ years in ML/AI research or engineering; 3+ years at senior/staff level MS or PhD in Computer Science, Machine Learning, or related field (or equivalent) 5+ years hands-on RL — environment design, reward engineering, policy optimization — with at least one production deployment LLM Post-Training 3+ years fine-tuning LLMs with hands-on RL post-training (RLHF, DPO, GRPO, PPO) Expert‑level implementation of RLHF pipelines, reward modeling (Bradley‑Terry), DPO, and KTO Working knowledge of modern post‑training and rollout‑serving libraries (TRL, veRL, OpenRLHF, SkyRL) Experience building LLM‑based agents: tool use, multi‑turn reasoning, trajectory evaluation Strong Python and software engineering skills — comfortable building production pipelines, not just notebooks RL Foundations Deep expertise in MDPs, policy gradient methods (PPO, SAC), and temporal difference learning Hands‑on experience with Gymnasium‑based environments and reward engineering (sparse vs. dense) Preferred Qualifications Publications at NeurIPS, ICML, ICLR, ACL, COLM, or similar venues Open‑source contributions to post‑training or agent frameworks (TRL, veRL, OpenRLHF, SkyRL) Experience with Offline RL (CQL, IQL), Model‑based RL / World Models, or Hierarchical RL Background in synthetic data generation, simulation, or world models Domain experience in healthcare, finance, logistics, or compliance Why Join Centific Lead the frontier. Shape a new discipline at the intersection of post‑training, simulation, and enterprise AI. Ship your science. See your research power real systems across healthcare, finance, and safety‑critical operations. Collaborate with leaders. Work alongside NVIDIA, Microsoft, and the global AI community. Build what matters. Create governed, compliant AI systems enterprises can actually trust. Learn more about us at centific.com. Centific 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. #J-18808-Ljbffr