Research Internship – Reinforcement Learning for Large Foundation Models

Research Internship in Reinforcement Learning for Large Foundation Models: Develop stable and efficient RL algorithms for large foundation models, conduct large-scale RL experiments in complex reasoning and autonomous agent scenarios, and explore RL algorithms, reward modeling, and world models. Collaborate with Tencent AI Lab researchers to deliver impactful algorithms for real-world applications and produce influential publications. Ideal candidates hold a Ph.D. in Computer Science, Machine Learning, Artificial Intelligence, or related fields from a top university, with research experience in NLP or ML, proficiency in Python and PyTorch, and a strong publication track record, plus excellent communication and teamwork for cross-functional collaboration. Internship lasts 3 months with possible extension; can start anytime in 2026; base pay range between $80,168.40 and $124,800 per year; paid sick leave, holidays, and company-sponsored medical plan eligibility for full-time interns.