Student Researcher (LLM Post Training - Agent & Reinforcement Learning) - 2026 Start (PhD)

Beijing ByteDance Technology Co Ltd

  • San Jose, CA
  • 30+ days ago

    Highlights

    The team's goal is to research and explore next-generation advanced technologies such as SFT, RM, RL, and self-learning during the posttrain phase, while significantly optimizing and improving key areas including reasoning, coding, agent, and omni model. About the team The Seed LLM Post Training team is responsible for researching cutting-edge posttrain technologies and providing core posttrain capabilities for unified multimodal large models.

    Numbers & Facts

    LocationSan Jose, CA

    Description

    About the team The Seed LLM Post Training team is responsible for researching cutting-edge posttrain technologies and providing core posttrain capabilities for unified multimodal large models. The team's goal is to research and explore next-generation advanced technologies such as SFT, RM, RL, and self-learning during the posttrain phase, while significantly optimizing and improving key areas including reasoning, coding, agent, and omni model.

    Responsibilities

    • Explore large-scale models and optimize systems.
    • Data construction, instruction tuning, preference alignment, and model optimization.
    • Improving relevant model capabilities, such as reasoning, code, math etc.
    • In-depth research and exploration of future use cases.Minimum Qualifications:
    • 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 in accredited ML/AI conferences (e.g., NeurIPS, ICLR, ICML).
    • Solid programming and experimentation skills, including with RL or LLM frameworks.

    Preferred Qualifications:

    • Experience with LLM agents, tool use, or prompt-based control.
    • Familiarity with environments such as WebArena, ALFWorld, or programmatic reasoning tasks.
    • Understanding of RL techniques such as reward shaping, memory augmentation, or curriculum learning.

    As a condition of employment, all successful candidates must be able to establish authorization to work in the United States. For this position, the Company does not provide sponsorship or any immigration-related benefits.

    Similar Jobs