Key skills
Reinforcement LearningMarkov Decision Processes (MDPs)Q-learningDeep Q-Network (DQN)Double DQNDueling DQNPolicy Gradient MethodsREINFORCEActor-CriticA2CA3CProximal Policy Optimization (PPO)Trust Region Policy Optimization (TRPO)Soft Actor-Critic (SAC)Temporal Difference Learning (TD(0), TD(λ))Gymnasium/OpenAI GymReward EngineeringSimulationOffline Reinforcement LearningConservative Q-Learning (CQL)Batch-Constrained Q-Learning (BCQ)Implicit Q-Learning (IQL)Model-based Reinforcement LearningDreamerMuZeroHierarchical Reinforcement LearningBehavioral CloningGenerative Adversarial Imitation Learning (GAIL)PythonRLlibStable BaselinesPyTorchJAXTensorFlowLarge Language Model (LLM) Fine-tuningReinforcement Learning with Human Feedback (RLHF)Direct Preference Optimization (DPO)Group-based Policy Optimization (GRPO)Agentic AIMulti-step Reasoning AgentsSoftware Engineering for Scalable PipelinesAIMLLLMAgentic
About this role
Centific is an AI research company focused on advancing foundational AI models and applications. As an Applied Reinforcement Learning Engineer, you will design and build RL environments to simulate enterprise workflows and train intelligent agents, ensuring that RL methodologies are effectively implemented in production systems.
Responsibilities:
- Design and build custom RL environments (digital twins) simulating enterprise workflows: document processing, compliance, onboarding, support automation
- 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
Requirements:
- Deep RL expertise: 3+ years hands-on experience with environment design, reward engineering, policy optimization
- LLM post-training: Experience fine-tuning LLMs using RLHF, DPO, PPO, or similar
- Production skills: Software engineering beyond research with scalable pipelines and training infrastructure
- Agentic AI: Experience with LLM-based agents, tool use, multi-step reasoning
- Technical stack: Strong Python; Gymnasium, RLlib, Stable Baselines; PyTorch/JAX/TensorFlow
- Education: MS/PhD in CS, ML, or related field (or equivalent experience)
- Publications at NeurIPS, ICML, ICLR, ACL, or similar venues
- Enterprise workflow experience in healthcare, finance, logistics, or compliance
- Open-source contributions to CleanRL, TRL, veRL, or agent frameworks
- Experience with world models, synthetic data generation, and simulation
- Distributed training and large-scale RL experimentation