Senior RL Research Scientist — Post-Training & Agent AI

Centific; United States; A distancia; USD 200.000 - 250.000; Jornada completa

Descripción de la vacante

Centific is a frontier AI data foundry seeking an experienced ML/AI engineer to design simulations, post‑train RL agents, and build end‑to‑end data‑to‑model pipelines for enterprise AI deployments. You will lead multi‑disciplinary teams, implement RLHF pipelines, and mentor researchers while translating research into production systems for healthcare, finance, and logistics.

This role requires 7+ years in ML/AI, a MS or PhD, and hands‑on RL with production deployments; familiarity with

Formación

• 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
• 5+ years hands‑on RL — with at least one production deployment

Responsabilidades

• 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
• Mentor researchers and engineers; drive technical direction through influence
• Translate research into production; contribute to publications

Conocimientos

Python programming

Machine Learning

Reinforcement Learning

Software engineering

Mentoring

Educación

MS or PhD in Computer Science, Machine Learning, or related field

Herramientas

TRL

veRL

OpenRLHF

SkyRL

Gymnasium

Descripción del empleo

Centific is a frontier AI data foundry seeking an experienced ML/AI engineer to design simulations, post‑train RL agents, and build end‑to‑end data‑to‑model pipelines for enterprise AI deployments. You will lead multi‑disciplinary teams, implement RLHF pipelines, and mentor researchers while translating research into production systems for healthcare, finance, and logistics.

This role requires 7+ years in ML/AI, a MS or PhD, and hands‑on RL with production deployments; familiarity with