Responsibilities
- Understand business requirements and apply LLM post-training technologies including SFT, RLVR, and Agent RL.
- Optimize models for information extraction, intent classification, and tool calling across payment-related business scenarios.
- Design and build agent architectures such as ReAct, Plan-Act, Generate-Verifier, and Multi-Agent systems.
- Explore Agent Test-Time-Scaling technology.
- Track LLM research developments and identify solutions for new business scenarios.
Requirements
- Excellent programming fundamentals and proficiency in at least one language such as Python or C++.
- Familiarity with NLP, computer vision, and machine learning technologies.
- Deep knowledge of LLM technologies including Reward Models, GRPO, PPO, DPO, SFT, and RFT.
- Proficiency with open-source model fine-tuning and training frameworks such as LLaMA Factory and Verl.
- Familiarity with inference acceleration frameworks such as vLLM and understanding of open-source models such as Qwen and DeepSeek.
- Strong problem-solving, communication, and teamwork skills.
- Experience training, fine-tuning, and delivering large models, implementing LLM application products, publishing papers at relevant top conferences, or competing in ACM/ICPC, NOI/IOI, TopCoder, or Kaggle is preferred.
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.