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

Join the Seed LLM Post Training team to research and improve next-generation post-train capabilities for unified multimodal large models. You’ll explore large-scale models, build data for instruction tuning and preference alignment, and optimize systems to enhance reasoning, coding, math, and agent/omni-model performance. The role includes in-depth research into future use cases, with mentorship and collaboration as part of a 2026 PhD internship.