Responsibilities
- Develop and optimize LLM inference frameworks.
- Optimize GPU and CUDA performance to create a high-performance LLM inference engine.
- Build and maintain large-scale, heterogeneous, distributed ML systems integrating GPU, NPU, RDMA, and storage technologies.
- Perform performance analysis and optimization for reliable, scalable ML training and inference services.
Requirements
- Bachelor’s degree or above in computer, electronics, automation, software, or a related field.
- Proficiency in C/C++ and algorithms and data structures, with familiarity with Python.
- Understanding of deep learning algorithms and neural network architecture.
- Familiarity with deep learning training frameworks such as PyTorch.
- Preferred: proficiency in CUDA-based GPU high-performance computing optimization, computer architecture, parallel computing optimization, memory access optimization, and low-bit computing.
- Preferred: familiarity with TensorRT-LLM, ORCA, and vLLM.
- Preferred: knowledge of LLM models and experience accelerating LLM model optimization.
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.