Senior Applied RL Engineer — Enterprise AI & Simulation

Centific; United States; Hybrid; USD 150,000 - 300,000; Full time

Job summary

Centific in the United States is seeking a Senior Applied Reinforcement Learning Engineer to design RL environments that simulate complex enterprise workflows and train intelligent agents. You will bridge RL research and production, building end-to-end pipelines and post-training methods to improve AI agent performance.

The role requires deep RL expertise, LLM post-training experience, and production-grade software skills. Hybrid/remote work in the US with competitive compensation is offered.

Qualifications

• Deep RL expertise with environment design and reward engineering.
• Experience fine-tuning LLMs using RLHF, DPO, PPO, or similar.
• Production software engineering with scalable pipelines and training infra.
• Experience with LLM-based agents, tool use, multi-step reasoning.
• Strong Python and RL tooling knowledge (Gymnasium, RLlib, Stable Baselines).
• MS/PhD in CS, ML, or related field (or equivalent).

Responsibilities

• Design and build custom RL environments (digital twins) simulating enterprise workflows.
• Post-train LLM-based agents on domain-specific tasks using PPO, GRPO, DPO, RLHF.
• Build end-to-end pipelines converting human-labeled traces into RL data.
• Architect multi-step reasoning agents with tool-calling and closed learning loops.
• Design reward functions, verifiers, and validation frameworks for pre-deployment testing.
• Translate cutting-edge RL research into production systems; contribute to publications.

Skills

Deep RL

LLM post-training

Production engineering

Agentic AI

Python & RL toolkits

MS/PhD in CS/ML

Education

MS/PhD in CS/ML

Tools

Gymnasium

RLlib

Stable Baselines

PyTorch

TensorFlow

JAX

Job description

Centific in the United States is seeking a Senior Applied Reinforcement Learning Engineer to design RL environments that simulate complex enterprise workflows and train intelligent agents. You will bridge RL research and production, building end-to-end pipelines and post-training methods to improve AI agent performance.

The role requires deep RL expertise, LLM post-training experience, and production-grade software skills. Hybrid/remote work in the US with competitive compensation is offered.