Responsibilities
- Design, implement, and optimize high-performance GPU kernels for large-scale LLM/VLM inference, including attention and GEMM operators.
- Develop and tune inference kernels using CUDA and Triton.
- Drive end-to-end performance optimization of production inference systems at scale.
- Conduct performance analysis and profiling across kernel-level and serving-level components.
- Collaborate with research and infrastructure teams to deploy kernel- and compiler-level optimizations in production.
Requirements
- Bachelor's degree or above in Computer Science, Electrical Engineering, or a related field.
- Strong proficiency in C/C++ and Python, with solid foundations in algorithms, data structures, and systems programming.
- Hands-on experience optimizing LLM/VLM inference with demonstrated impact on latency, throughput, or serving cost.
- Hands-on experience writing and optimizing GPU kernels in CUDA and/or Triton.
- Deep understanding of GPU architecture, including memory hierarchy, occupancy, and instruction throughput, with solid optimization experience.
- Preferred: experience with ML compiler internals such as Triton, MLIR, or LLVM.
- Preferred: contributions to related open-source projects such as Triton, vLLM, SGLang, FlashAttention, or CUTLASS.
- Preferred: publications in relevant venues such as MLSys, OSDI, or ASPLOS.
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.