[Skip to main content](#main-content) [OpenNash Jobs](https://jobs.opennash.com/) [Hiring report](/reports/hiring/) · [All Kuaishou Technology jobs](https://jobs.opennash.com/companies/kuaishou-technology/) · [Search jobs](/search/) Kuaishou Technology · Beijing, Shenzhen # 大模型推理工程师（LLM Inference） Beijing, Shenzhen Listed on Kuaishou Technology’s official careers site. Listed as of October 19, 2026. Check that it is still open and apply there. [Apply on Kuaishou Technology’s careers site →](https://zhaopin.kuaishou.cn/#/official/social/job-info/29268) [OpenNash Jobs](https://jobs.opennash.com/) / [Kuaishou Technology](https://jobs.opennash.com/companies/kuaishou-technology/) / 大模型推理工程师（LLM Inference） ## Job description 【关于我们】 我们全面打造 AI Infra：大模型训练、推理引擎，为公司核心大模型(基模+MaaS)场景提供高速、稳定、可扩展、低成本的大模型训练与推理服务； 在这里，你将参与推动分布式训练、强化学习（RL）、微调（SFT）、算子优化、混合精度与量化加速、KV Cache 管理、推理调度与 Pipeline 优化等前沿技术落地，让训练更快、推理更省、交付更稳； 【职位描述】 - 负责大模型推理引擎的研发与优化，提升吞吐、降低时延与推理成本； - 负责推理核心模块建设，包括 KV Cache 管理、Batching/Scheduling、Prefill/Decode Pipeline、PD 分离等； - 负责推理性能优化，面向 TTFT/TPOT/TPS/RPM 等指标进行系统级优化（算子、显存、通信、调度）； - 负责推理侧算子研发与优化，包括算子融合、Kernel 优化、图优化、推理编译优化，以及 INT8/FP8/FP4 等量化推理加速方案落地； - 负责推理稳定性与高可用建设，包括故障恢复、限流降级、容量评估、自动化诊断与 SLA 保障； - 推动推理平台化能力建设，包括模型发布流程、灰度、监控、日志、Tracing 与自动化运维工具链。 - 本科及以上学历，计算机/软件相关专业； - 熟练掌握 C++/Python，具备高性能系统研发能力； - 熟悉 Transformer 推理原理，理解 Attention、KV Cache、采样策略等机制； - 熟悉主流推理框架或推理引擎（TensorRT/Sglang/vLLM 等）； - 熟悉 GPU/NPU 性能调优与 profiling，能定位性能瓶颈并推动优化落地； - 熟悉推理侧算力优化技术，包括算子融合、图优化、Triton/CUDA Kernel、推理量化与推理编译加速等； - 熟悉 Linux、网络与容器化（Docker/K8s），具备线上系统运维与稳定性经验优先。 ### 加分项 - 有大规模在线推理落地经验，熟悉高并发、长上下文、多租户调度等场景； - 熟悉 KV Cache 压缩/复用、请求迁移恢复、跨实例调度等关键能力； - 有通信优化经验（NCCL/HCCL/RDMA）； - 有推理量化落地经验（如GPTQ/AWQ 等）或推理加速相关经验； - 有国产卡适配经验（昇腾/寒武纪/沐曦等）。 ## At a glance - Posted by the employer: Not stated - First seen by OpenNash: Oct 19, 2026 - Last checked: Oct 19, 2026 - Listed for: Under a day - Location: Beijing, Shenzhen[Apply on Kuaishou Technology’s careers site →](https://zhaopin.kuaishou.cn/#/official/social/job-info/29268) ## More jobs at Kuaishou Technology ### [Aigc多模态数据系统研发工程师/专家](https://jobs.opennash.com/companies/kuaishou-technology/jobs/54012af394181f20f7ce/) Beijing, Shenzhen ### [Human Centric生成算法专家-【可灵AI】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/26a05cd6c4f638d345df/) Beijing, Shenzhen ### [云网络研发工程师](https://jobs.opennash.com/companies/kuaishou-technology/jobs/4510ca6c07959fd91b76/) Beijing, Shenzhen ### [全栈开发工程师（数据平台方向）-【可灵AI专项】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/5af42ab3a44a574e78a6/) Beijing, Shenzhen ### [具身智能仿真技术专家-【可灵AI】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/7cdb7c9defde80540207/) Beijing, Shenzhen ## Similar jobs at other companies ### [PhD Thesis: Optimization of LLM / FM Inference in Industrial Edge Networks](https://jobs.opennash.com/companies/siemens/jobs/13fcd252cb94716460a9/) Siemens ### [Senior Software Engineer, LLM Inference](https://jobs.opennash.com/companies/nvidia/jobs/b597b4d2c8ca831c187f/) NVIDIA · Israel, Tel Aviv ### [Senior Performance Engineer - LLM Inference Frameworks](https://jobs.opennash.com/companies/nvidia/jobs/a28f15d7e8f86da39c2b/) NVIDIA ### [AI Engineer 5 (FM Hosting, LLM Inference)](https://jobs.opennash.com/companies/capital-one-financial/jobs/095fe4d0782adc54b6aa/) Capital One Financial ### [AI Engineer 5 (FM Hosting, LLM Inference)](https://jobs.opennash.com/companies/capital-one-financial/jobs/98e0fb901069e6998878/) Capital One Financial OpenNash lists jobs from employers’ own careers sites and does not handle applications. Dates come from the employer where stated; “first seen” and “last checked” are our own observations. OpenNash Jobs · Official listings with dates and links to the employer. [Weekly hiring report](/reports/hiring/) · [Methodology](/methodology/)