Senior Engineer, On-Device Agentic OS

LenovoBeijing, BeijingOn-siteFull-timeSenior, 5–8 yearsListed 3 hours ago

Apply now

About this role

We are Lenovo. We do what we say. We own what we do. We WOW our customers.
Lenovo is a US$83 billion revenue global technology powerhouse, ranked #153 in the Fortune Global 500, and serving millions of customers every day in 180 markets. Focused on a bold vision to deliver Smarter Technology for All, Lenovo has built on its success as the world’s largest PC company with a full-stack portfolio of AI-enabled, AI-ready, and AI-optimized devices (PCs, workstations, smartphones, tablets), infrastructure (server, storage, edge, high performance computing and software defined infrastructure), software, solutions, and services. Lenovo’s continued investment in world-changing innovation is building a more equitable, trustworthy, and smarter future for everyone, everywhere. Lenovo is listed on the Hong Kong stock exchange under Lenovo Group Limited (HKSE: 992) (ADR: LNVGY).
This transformation together with Lenovo’s world-changing innovation is building a more inclusive, trustworthy, and smarter future for everyone, everywhere. To find out more visit www.lenovo.com (https://www.lenovo.com), and read about the latest news via our StoryHub (https://news.lenovo.com/).

- 核心职责 负责端侧 Agentic OS 框架架构设计,包括任务编排、工具调用、上下文/记忆管理、token routing、device-cloud task orchestration、资源调度与推理运行时协同。

- 建立并 owner 端到端指标体系与 benchmark:P50/P95/P99 推理时延、tokens/s 吞吐、CPU/GPU/NPU 资源利用率、内存占用、功耗/热约束、模型精度、Agent 召回率、整体任务完成质量。

- 驱动跨层优化闭环:结合 FP4/INT4 QAT、speculative decoding、on-policy distillation、运行时优化与异构调度,实现端侧性能与质量联合提升。

- 面向 CPU/GPU/NPU 异构计算和 Windows/Linux/Android 等端侧环境,定义框架约束、降级策略、设备云协同策略与隐私保护机制。

- 将算法创新和推理优化转化为可部署、可度量、可复用的系统能力。

- 负责技术路线、风险识别、里程碑拆解和跨团队对齐,对框架上线效果和指标结果负责。

- 任职要求 硕士及以上学历,人工智能、计算机科学、电子信息技术等相关专业;

- 软硬件一体优化能力,面向特定硬件的算子设计与优化能力。

- 具备以下至少一到两个方向的深入研究或实践经验:大语言模型、多模态大模型、大模型后训练、大模型预训练、强化学习;

- 深入掌握Transformer架构,了解主流dense和MoE开源模型(Qwen, Deepseek等)的结构设计原理;

- 具备端侧 AI 系统、Agent 框架、推理运行时、OS 调度或异构计算相关经验。

- 熟悉端侧模型部署与优化链路,包括量化、压缩、编译、运行时、内存管理、算子优化中的至少多个方向。

- 具备强指标意识,能用 benchmark 和线上/离线数据定义问题、验证收益并推动闭环。

- 熟悉 C++/Python,具备较强架构设计、性能剖析和跨团队推动能力。

- 对 token routing、device-cloud 编排、多模态端侧推理、隐私保护个性化之一有深入实践。

- 加分项 有端侧 Agent 产品化经验;有 NPU/GPU 异构调度经验;有量化训练、投机解码、蒸馏落地经验;有顶会论文/专利或开源影响力。