广告大模型训练/推理优化研发工程师-Data
Core
Optimizing deep learning engines for training and inference, developing high-performance operators, and supporting large-scale distributed systems.
Role type
Senior IC machine-learning infrastructure engineer (training/inference optimization)
Builds
High-performance operator libraries, distributed training/inference frameworks, and optimized deep learning engines
Domain
Artificial Intelligence / High-Performance Computing
Deliverable
production ML models
Required skills
C/C++/Python, CUDA, Triton, distributed training (FSDP/DeepSpeed), inference frameworks (vLLM/SGLang), SIMD, heterogeneous hardware adaptation
Preferred skills
AscendC, BangC, DCU, next-gen hardware architecture exploration
Responsibilities
Deep optimization of training and inference engines including compilation and graph fusion; Research and development of high-performance operator libraries; Support for long-sequence large-scale distributed training and inference; Survey and implement frontier technologies for production
Seniority
Senior, hands-on IC
