Research Intern — Applied Reinforcement Learning @ Centific

Research Intern — Applied Reinforcement Learning at Centific. Location: Palo Alto or Redmond or United States. Role: designing pipelines, training agents, evaluating systems Requirements: PhD candidate in CS/ML or related field; strong Python and PyTorch with GPU training experience; solid RL fundamentals and RLHF/DPO/PPO experience; strong experimentation and reporting skills. Category: Research and Development (R&D) Seniority: Entry Level Tools: Python, PyTorch, CUDA, Gymnasium, RLlib, Stable Baselines, TRL, Weights & Biases, FastAPI, gRPC, ONNX, TensorRT Commitment: Full Time, Contract Workplace: Remote Languages: English