Principal Research Scientist: AI Systems & RL in Production

Centific; East Palo Alto (CA); Sur place; USD 250 000 - 300 000; Plein temps

Résumé du poste

Centific is seeking a senior ML/AI leader to design simulation environments and digital twins for enterprise workflows, and to post-train LLM agents using RLHF, DPO, GRPO, and PPO. You will architect multi-turn, tool-using agents and build end-to-end data pipelines for training data.

Lead the technical direction, mentor researchers, and translate research into production. Join a team of PhDs and engineers tackling high-impact GenAI challenges at scale.

Qualifications

• 7+ years in ML/AI research or engineering.
• 3+ years at senior/staff level with MS/PhD or equivalent.
• 5+ years hands-on RL with at least one production deployment.

Responsabilités

• 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.

Connaissances

Python

ML research

RLHF

PPO

Formation

MS/PhD in CS/ML

Outils

TRL

veRL

OpenRLHF

SkyRL

Gymnasium

Description du poste

Centific is seeking a senior ML/AI leader to design simulation environments and digital twins for enterprise workflows, and to post-train LLM agents using RLHF, DPO, GRPO, and PPO. You will architect multi-turn, tool-using agents and build end-to-end data pipelines for training data.

Lead the technical direction, mentor researchers, and translate research into production. Join a team of PhDs and engineers tackling high-impact GenAI challenges at scale.