Research Intern – Reinforcement Learning for Large Foundation Models @ Tencent

Research Intern – Reinforcement Learning for Large Foundation Models at Tencent. Location: Singapore. Role: designing algorithms, training models, developing rewards Requirements: Enrolled in a Master's or PhD in CS/ML, strong RL fundamentals, Python and PyTorch proficiency, multi-GPU training experience, research publication or equivalent maturity. Category: Research and Development (R&D) Seniority: Entry Level Tools: Python, PyTorch, DeepSpeed, FSDP, Megatron Commitment: Part Time Workplace: Onsite Languages: English