Centific
Senior Applied Reinforcement Learning Engineer
$150K–$300K
Remote Work( USA) · Senior · Full-time · Posted Sep 17, 2026
- Experience
- 3+ years hands-on deep RL experience.
- Education
- MS/PhD in CS, ML, or related field (or equivalent experience).
About the job
Designs simulated enterprise workflows and post-training pipelines to improve LLM-based agents using reinforcement learning.
What you'll do
- Build custom RL environments, reward functions, verifiers, and validation frameworks for enterprise workflows.
- Post-train LLM agents and convert human-labeled traces into RL training data.
- Develop multi-step, tool-using agents and translate RL research into production systems.
What they ask for
- 3+ years of hands-on experience in deep RL, including environment design, reward engineering, and policy optimization.
- Experience fine-tuning LLMs using RLHF, DPO, PPO, or similar methods; experience with LLM agents, tool use, and multi-step reasoning.
- Production software engineering experience with scalable pipelines and training infrastructure.
- Strong Python; experience with Gymnasium, RLlib, Stable Baselines, and PyTorch/JAX/TensorFlow.
Nice to have
- Publications at NeurIPS, ICML, ICLR, ACL, or similar venues.
- Enterprise workflow experience, open-source contributions, or experience with world models, synthetic data, simulation, or distributed training.
Pay
$150K - $300K Annually (base salary)
Tools
Python, Gymnasium, RLlib, Stable Baselines, PyTorch, JAX, TensorFlow, PPO
AI focus
Build and train reinforcement-learning environments and LLM-based agents, including alignment and post-training using human feedback, preference optimization, and reward modeling.
Model-written summary · the original posting is authoritative