llm服务部署工程师
北京、上海
全职
职位描述
岗位职责 1. 负责LLM从预训练模型到边缘推理服务的完整集成与落地,搭建LLM服务化CI/CD流水线,实现模型量化、编译优化、前后处理标准化和推理服务一键部署。 2. 设计开发边缘LLM推理服务流水线,支持主流推理引擎(SGLang、vLLM、Nano-LLM)的自动集成、性能测试、服务封包、版本发布,保障模型在边缘设备上的稳定运行。 3. 针对边缘设备资源受限场景,设计并实现模型量化压缩方案(AWQ、GPTQ、GGUF/INT4/INT8),优化模型推理延迟与内存占用,确保在Jetson Nano/Xavier等边缘设备上的高效运行。 4. 开发模型微调(Fine-tune)标准化流程,支持基于LoRA/QLoRA的参数高效微调,实现数据预处理、训练、评估、部署的全流程自动化。 5. 开发业务方常用的压测、回测、精度排查、服务调用等功能工具,提供性能监控、日志追踪、错误诊断等运维能力,保障LLM服务在边缘环境的高可用性。
职位要求
投递

AGIBOT is an Embodied AI foundation model company developing both the intelligence layer and the corresponding robotic embodiments needed to bring general intelligence into the physical world. Founded in 2023, AGIBOT is building a full-stack Embodied AI platform across foundation models, data infrastructure, simulation, robotic hardware, and deployment. AGIBOT’s “Three Intelligences in One” architecture integrates Locomotion Intelligence, Interaction Intelligence, and Manipulation Intelligence into a unified embodied system. AGIBOT’s portfolio spans humanoid robots, quadrupeds, dexterous systems, and commercial cleaning solutions. In March 2026, AGIBOT announced that its 10,000th robot had rolled off the production line.