Research Intern — Applied Reinforcement Learning

Role Description

Centific AI Research seeks a PhD Research Intern to design and evaluate reinforcement learning (RL) systems for agentic AI workflows. You will develop RL environments, reward models, and post-training pipelines for LLM-based agents, translating research into practical enterprise solutions.

Scope of Work

• End-to-end RL pipelines for agentic systems (simulation → training → evaluation)
• Alignment of LLM-based agents using RLHF, DPO, PPO, and emerging methods
• Design of reward functions, verifiers, and evaluation frameworks
• Simulation environments (digital twins) for enterprise workflows
• Scalable training and inference for RL-based systems

Example Projects

• Build a custom RL environment simulating a real-world enterprise workflow and train an agent using PPO or GRPO
• Develop a reward modeling pipeline from human feedback and evaluate alignment improvements
• Create an evaluation harness measuring reasoning, task success, and policy safety
• Prototype an agentic system with tool use and multi-step reasoning, integrated with RL training
• Document experiments, ablations, and findings for research and productionization

Qualifications

• PhD candidate in CS, ML, or related field with research in reinforcement learning or agentic AI
• Strong Python and PyTorch skills with GPU-based training experience
• Solid understanding of RL fundamentals (MDPs, policy gradients, value methods)
• Experience with LLMs and post-training techniques (RLHF, DPO, PPO, etc.)
• Strong experimentation practices (ablation, reproducibility, clear reporting)

Requirements

• Experience with RL environments (Gymnasium, RLlib, Stable Baselines)
• Research in offline RL, model-based RL, or hierarchical RL
• Publications at top ML conferences (NeurIPS, ICML, ICLR, ACL)
• Experience with simulation, synthetic data, or multi-agent systems
• Distributed training and large-scale experimentation

Tech Stack

• PyTorch, CUDA; RL libraries (Gymnasium, RLlib, Stable Baselines)
• LLM frameworks and post-training tools (TRL, custom RLHF pipelines)
• Experiment tracking (Weights & Biases)
• APIs/services (FastAPI, gRPC); optimization (ONNX, TensorRT)

Logistics

• Location: Palo Alto, CA (Preferred), Redmond, WA (Preferred) or Remote
• Duration: 3–6 months

Benefits

• Competitive stipend and real-world impactful projects
• Mentorship from researchers and engineers
• Access to modern GPU infrastructure
• Opportunities to publish and present research