Centific

Applied Reinforcement Learning Engineer

Centific
Apply
2 months ago
Remote, United StatesMid Level

Base Salary

$150k - $300k/yr

Responsibilities

  • Design and build custom RL environments and digital twins that simulate complex enterprise workflows.
  • Post-train LLM-based agents on domain-specific tasks using PPO, GRPO, DPO, RLHF, and related methods.
  • Build end-to-end pipelines that convert human-labeled traces into RL training data.
  • Architect multi-step reasoning agents with tool-calling and closed learning loops.
  • Design reward functions, programmatic verifiers, and validation frameworks for pre-deployment testing.
  • Translate RL research into scalable production systems and contribute to publications.
  • Help shape product direction and make governed RL accessible to enterprise customers.

Requirements

  • At least 3 years of hands-on experience with RL environment design, reward engineering, and policy optimization.
  • Experience fine-tuning LLMs using RLHF, DPO, PPO, or similar techniques.
  • Production software engineering experience beyond research, including scalable pipelines and training infrastructure.
  • Experience with LLM-based agents, tool use, and multi-step reasoning.
  • Strong Python skills and experience with Gymnasium, RLlib, Stable Baselines, and PyTorch, JAX, or TensorFlow.
  • MS or PhD in computer science, machine learning, or a related field, or equivalent experience.
  • Preferred: publications at NeurIPS, ICML, ICLR, ACL, or similar venues.
  • Preferred: enterprise workflow experience in healthcare, finance, logistics, or compliance.
  • Preferred: open-source contributions to CleanRL, TRL, veRL, or agent frameworks.
  • Preferred: experience with world models, synthetic data generation, simulation, distributed training, and large-scale RL experimentation.

Benefits

  • Hybrid/remote work arrangement in Palo Alto, California or Seattle, Washington.
  • Opportunity to shape a new discipline at the intersection of reinforcement learning, simulation, and enterprise AI.
  • Opportunity to apply research to real systems across healthcare, finance, and safety.
  • Collaboration with NVIDIA, Microsoft, and the global AI community.

Tech Stack

PythonPyTorchTensorFlow

Categories

AI ResearchML Engineering
Centific

About Centific

1,001-5,000 employees
Contact me