Backend Inference Systems Engineer — High-Performance AI
Summary
Builds and optimizes high-performance inference services for large-scale AI models using C/C++ and Linux, focusing on concurrency and performance tuning.
ByteDance is seeking graduates to join the Data AML team, focusing on its machine learning mid-platform for large-scale model inference and training systems. The role emphasizes building high-performance inference services, optimizing core modules, and staying current with industry advancements.
Applicants should be ready to onboard by end of 2027 and apply to up to two positions. We welcome strong C/C++ programmers with Linux experience and a solid foundation in concurrency, performance tuning,