CareerPlanSign in

高级GPU推理工程师

Beijing, China💼 Full-time🗓 2026-09-28

Core

Design and optimize co-scaling inference architectures and GPU operator compilation for marketing business applications.

Role type

Senior GPU inference engineer (system programming)

Builds

High-performance inference frameworks and optimized GPU operators for marketing business

Domain

Marketing technology, GPU computing, deep learning inference

Deliverable

production ML models

Required skills

C++, CUDA, Linux system programming, data structures and algorithms, deep learning frameworks (TensorFlow/PyTorch), GPU optimization

Preferred skills

Long sequence processing experience, search/ad/recommendation (SAR) inference optimization, LLM inference optimization

Sourced via tencent · Listed on CareerPlan, which tracks 845,000+ jobs from 20+ sources.