ByteDance
Student Researcher - (Seed Model - LLM - Post Training, Agent & Reinforcement Learning) – 2026 Start (PhD)
San Jose, California · Internship · Posted Oct 28, 2026
- Education
- Currently pursuing a PhD in Computer Science, AI, or a related field.
- Visa sponsorship
- Must obtain and maintain work authorization in the United States; the company does not provide sponsorship or immigration-related benefits.
About the job
Research and develop post-training methods for large language and multimodal models, improving capabilities such as reasoning, coding, math, and agent behavior.
What you'll do
- Explore large-scale models and optimize systems.
- Construct data, perform instruction tuning and preference alignment, and optimize models.
- Research future use cases and improve model capabilities, including reasoning, code, and math.
What they ask for
- Currently pursuing a PhD in Computer Science, AI, or a related field.
- Research experience in reinforcement learning, sequential decision-making, or agent behavior.
- First-author publications at accredited ML/AI conferences, such as NeurIPS, ICLR, or ICML.
- Solid programming and experimentation skills, including with RL or LLM frameworks.
Nice to have
- Experience with LLM agents, tool use, or prompt-based control.
- Familiarity with WebArena, ALFWorld, or programmatic reasoning tasks; understanding of RL techniques such as reward shaping, memory augmentation, or curriculum learning.
Tools
SFT, RM, RL, LLM frameworks, WebArena, ALFWorld
AI focus
Research post-training methods, including SFT, RM, RL, and self-learning, for unified multimodal models; improve reasoning, coding, math, and agent capabilities.
Model-written summary · the original posting is authoritative