About this role
The role involves designing RL training recipes for large-scale reasoning models and building RL pipelines for autonomous agents. It also focuses on developing advanced reward signals and optimization techniques to improve model generalization and reasoning capabilities.
Candidates must be enrolled in a PhD or Master's program in Computer Science or a related field with a strong grasp of RL fundamentals and PyTorch. Proven research maturity through first-author publications at top ML/NLP venues is required.
What they're looking for
Reinforcement LearningPyTorchPythonLarge Language ModelsPPOGRPODeepSpeedFSDP
Frequently asked questions
What does a Research Intern – Reinforcement Learning for Large Foundation Models at Tencent do?
The role involves designing RL training recipes for large-scale reasoning models and building RL pipelines for autonomous agents. It also focuses on developing advanced reward signals and optimization techniques to improve model generalization and reasoning capabilities. Candidates must be enrolled …
What skills does this Research Intern – Reinforcement Learning for Large Foundation Models role need?
Key skills for this role include Reinforcement Learning, PyTorch, Python, Large Language Models, PPO, GRPO.
How much does a Research Intern – Reinforcement Learning for Large Foundation Models at Tencent pay?
The employer did not list a salary for this role. Most similar Singapore roles publish their band on the job page.
Is this Research Intern – Reinforcement Learning for Large Foundation Models role remote, hybrid, or on-site?
This role is on-site, based in Singapore.
How do I apply for this Research Intern – Reinforcement Learning for Large Foundation Models role?
You can apply directly on Tencent's careers page. ApplyLah can tailor your résumé and cover letter to this exact role in seconds first.