Responsibilities
- Build and implement compilation optimization systems for recommendation machine learning engines across graph, operator, and memory levels.
- Develop optimizations including graph-operator fusion and automatic operator generation to maximize hardware utilization.
- Collaborate with hardware and algorithm teams on hardware-software co-design and compilation strategies.
- Optimize PyTorch model import, conversion, and code generation for deployment to the recommendation engine.
- Analyze performance bottlenecks and implement compilation, memory, loop, operator, and inference optimizations.
Requirements
- Proficiency in an AI compiler framework such as Triton, MLIR, or TVM, with practical experience in customized compilation optimization and pass development.
- Experience with GPU or NPU compilation optimization and expertise in loop, memory, and operator optimization.
- Familiarity with model structures and compilation adaptation logic in PyTorch and TensorFlow.
- Ability to independently analyze performance bottlenecks and implement technical optimizations.
- Preferred: experience with recommendation machine learning engine architecture, large-scale recommendation systems, low-latency inference, and high-concurrency compilation optimization.
- Preferred: contributions to open-source AI compiler projects such as TVM or MLIR, or expertise in large-model compilation adaptation and sparse operator generation.
Tech Stack
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.