大模型推理优化工程师
北京、上海
全职
通用智能板块
职位描述
职位描述 2、负责小鹏大模型推理技术在物理AI场景下的工程搭建及落地，包括但不限于自动驾驶，舱驾融合，机器人等场景 2、负责小鹏大模型推理引擎XLLM的核心特性开发，包括但不限于kv cache管理，FlashAttention设计及优化，投机解码 3、负责小鹏大模型推理引擎XLLM的加速优化，包括模型结构优化（MoE，Diffusion）及底层计算加速（INT4、INT8）。 4、负责小鹏大模型压缩技术探索，涵盖量化（QAT/PTQ）、剪枝、蒸馏、稀疏化、NAS等 职位要求 硕士研究生及以上学历，计算机及相关专业； 有扎实的数据结构与算法基础，熟悉python或C/C++。 熟悉并掌握主流模型压缩技术，如量化（GPTQ/AWQ/SmoothQuant）、剪枝（Sheared-LLaMa）、蒸馏及NAS。 3、熟悉LLM推理框架（如vLLM，SGLang，TensorRT-LLM）及优化加速技术（如Flashattention、KV Cache Management，Speculative-Decoding）。 4、具备LLM推理优化和加速技术的实践经验。 5、拥有深入研究精神、创新能力及持续学习意愿。 加分项： 1、熟悉GPU/NPU硬件架构，能使用CUDA、CUTLASS进行编程优化。 2、有异构计算加速或芯片级性能调优经验。
职位要求
投递
XPeng is a leading Chinese Smart EV company that designs, develops, manufactures, and markets Smart EVs that appeal to the large and growing base of technology-savvy middle-class consumers. Its mission is to drive Smart EV transformation with technology and data, shaping the mobility experience of the future. In order to optimize its customers’ mobility experience, XPeng develops in-house its full-stack advanced driver-assistance system technology and in-car intelligent operating system, as well as core vehicle systems including powertrain and the electrical/electronic architecture. XPeng is headquartered in Guangzhou, China. In 2021, the Company established its European headquarters in Amsterdam, along with other dedicated offices in Copenhagen, Munich, Oslo, and Stockholm.The Company’s Smart EVs are mainly manufactured at its plant in Zhaoqing and Guangzhou，Guangdong province.
For more information, please visit https://heyxpeng.com.
