大模型推理优化工程师-PICO
Core
Develop and optimize large model training and inference systems, integrating heterogeneous hardware and collaborating with algorithms for joint optimization.
Role type
Senior IC large model inference optimization engineer
Builds
High-performance training and inference systems for large language models
Domain
AI/ML infrastructure, Large Language Models (LLMs), Heterogeneous Computing
Deliverable
production ML models
Required skills
C/C++, Python, Linux, Machine Learning frameworks (TensorFlow/PyTorch/MxNet), Large model inference frameworks (vLLM/TensorRT-LLM/SGLang/Megatron-LM), Heterogeneous hardware integration (GPU/NPU/TPU), System performance optimization
Preferred skills
Algorithm-system co-optimization experience, Complex problem decomposition
Technologies
vLLM, TensorRT-LLM, SGLang, Megatron-LM, TensorFlow, PyTorch, MxNet, Linux, C/C++, Python
Responsibilities
Develop and optimize large model training and inference systems; Integrate heterogeneous hardware (GPU, NPU, TPU) into training and inference frameworks; Collaborate with algorithm teams for joint optimization of algorithms and systems.
