游戏AI-高性能推理系统研发专家
Core
Design and develop high-performance computing (HPC) systems for training and inference of large language models (LLMs) and AIGC on GPU clusters.
Role type
Senior IC GPU systems engineer (LLM inference/training)
Builds
High-throughput LLM inference and training pipelines for Tencent's 'Kaiwu' platform
Domain
AI infrastructure / GPU computing / Large Language Models
Deliverable
production ML models
Required skills
GPU kernel optimization, CUDA/ROCm programming, distributed training frameworks, performance profiling, operator design
Preferred skills
MoE optimization, dynamic computation graph optimization, DeepSeek model optimization experience
Technologies
NVIDIA CUDA, AMD ROCm, vLLM, SGLang, Megatron-LM, DeepSpeed, PTX, Tensor Core
Sourced via tencent · Listed on CareerPlan, which tracks 846,000+ jobs from 20+ sources.