Senior Applied RL Engineer - Enterprise Simulation & LLMs

Centific Global Solutions, Inc.; United States; Hybrid; USD 150,000 - 300,000; Full time

Job summary

Centific is seeking a Senior Applied Reinforcement Learning Engineer to design RL environments that simulate enterprise workflows and train intelligent agents. The role sits at the intersection of RL research and production systems, translating customer needs into bespoke simulation environments and post-training pipelines.

You will work with foundational RL methods and modern LLM-based agent architectures, shaping product direction and enabling safe, compliant AI improvements for enterprise

Qualifications

• Deep RL expertise with 3+ years hands-on experience in environment design, reward engineering and policy optimization.
• Experience fine-tuning LLMs using RLHF, DPO, PPO, or similar.
• Production-grade software engineering for scalable ML pipelines and training infra.

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, and RLHF.
• Build end-to-end pipelines converting human-labeled traces into RL training 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

Python

RLlib

Stable Baselines

LLM agents

Education

MS/PhD in CS/ML

Tools

Gymnasium

PyTorch

JAX

TensorFlow

Job description

Centific is seeking a Senior Applied Reinforcement Learning Engineer to design RL environments that simulate enterprise workflows and train intelligent agents. The role sits at the intersection of RL research and production systems, translating customer needs into bespoke simulation environments and post-training pipelines.

You will work with foundational RL methods and modern LLM-based agent architectures, shaping product direction and enabling safe, compliant AI improvements for enterprise