Responsibilities
- Build and evolve agent runtimes and harnesses that orchestrate skills, tools, and context for creator and seller agents.
- Engineer agentic memory, context compaction and editing, observation masking, and just-in-time retrieval for long multi-turn interactions.
- Post-train and fine-tune LLMs using SFT, DPO, and RL, and develop data flywheels from served conversations for training, evaluation, and retrieval signals.
- Design and integrate tools, Skills, MCP connectors, and tool-search systems for large tool inventories.
- Build LLM evaluation systems with human-agreement calibration and regression, safety, cost, and latency-aware harnesses.
- Develop self-evolving replay, task/environment simulation, Auto-RCA, Auto-GSB, and Auto-Policy loops.
- Own an end-to-end production surface deployed across 30+ languages and measured by GMV, content, and creator/merchant satisfaction.
Requirements
- Currently pursuing a bachelor's degree in software development, computer science, computer engineering, or a related technical discipline.
- Strong Python skills plus proficiency in at least one of C++, Go, Rust, or Java.
- Solid machine learning, deep learning, and natural language processing fundamentals with hands-on LLM or agent experience.
- Experience may come from coursework, research, an internship, competition, open source, or a serious side project.
- Ability to read a research paper or engineering blog and turn its ideas into working code.
- Preferred qualifications include pursuing a master's degree in a relevant technical discipline.
- Preferred hands-on depth includes post-training, agent systems, evaluation, inference and serving, or multilingual NLP.
Benefits
- Internship program provides hands-on experience, industry exposure, and opportunities to apply knowledge to real-world challenges.
- Interns can explore career paths and participate in social events, learning programs, and development workshops with industry professionals.
- Applications are reviewed on a rolling basis, and candidates should state availability and start and end dates on their resumes.
Categories
About ByteDance
ByteDance is a global incubator of platforms at the cutting edge of commerce, content, entertainment and enterprise services - over 2.5bn people interact with ByteDance products including TikTok. Creation is the core of ByteDance's purpose. Our products are built to help imaginations thrive. This is doubly true of the teams that make our innovations possible. Together, we inspire creativity and enrich life - a mission we aim towards achieving every day. At ByteDance, we create together and grow together. That's how we drive impact - for ourselves, our company, and the users we serve. We are committed to building a safe, healthy and positive online environment for all our users. We have over 110,000 employees based in more than 30 countries globally. Join us.