[Skip to main content](#main-content) [OpenNash Jobs](https://jobs.opennash.com/) [Hiring report](/reports/hiring/) · [All Tencent Holdings jobs](https://jobs.opennash.com/companies/tencent-holdings/) · [Search jobs](/search/) Tencent Holdings · Beijing # 大模型推理后台链路工程师（语音方向）（北京/深圳/上海） Beijing Listed on Tencent Holdings’s official careers site. Listed as of October 19, 2026. Check that it is still open and apply there. [Apply on Tencent Holdings’s careers site →](https://careers.tencent.com/en-us/jobdesc.html?postId=2092937311057788928) [OpenNash Jobs](https://jobs.opennash.com/) / [Tencent Holdings](https://jobs.opennash.com/companies/tencent-holdings/) / 大模型推理后台链路工程师（语音方向）（北京/深圳/上海） ## Job description ### 推理后台链路建设 - 负责语音大模型推理后台链路的整体设计与实现，覆盖接入层、调度层、推理层、流式返回、落盘与全链路监控； ### 流式语音服务架构 - 构建实时语音对话（语音进—语音出）的流式推理服务，优化首字延迟（TTFB）、端到端延迟与实时率（RTF），保障交互流畅性； ### 推理引擎与 GPU 优化 - 负责 GPU 推理引擎优化，包括算子优化、量化（INT8/FP8）、KV Cache 管理、投机解码、Continuous Batching、显存与吞吐优化，提升单卡推理效率与性价比； ### 分布式推理与弹性调度 - 建设多机多卡推理能力（张量并行 / 流水线并行）、多模型编排、弹性扩缩容、负载均衡与故障自愈机制； ### 稳定性与工程化 - 建设高可用架构、灰度发布、全链路监控告警、压测与容量规划，保障推理服务的稳定性与可观测性； ### 前沿技术落地 - 跟进语音大模型与推理框架的前沿进展，推动新技术在业务中的落地。 Requirements 1.本科及以上学历，计算机、软件工程、电子信息等相关专业； 2.2年以上后端 / 基础架构 / 在线服务开发经验，有大规模高并发在线服务建设经验； 3.精通 C++ / Go / Python至少一门语言，具备扎实的 Linux 系统、网络编程与并发编程功底； 4.熟悉主流深度学习推理框架（TensorRT、vLLM、Triton Inference Server、ONNX Runtime等至少一种），有实际推理服务优化落地经验； 5.熟悉CUDA 编程与 GPU 算子优化，理解显存、带宽、算子调度等底层机制； 6.熟悉分布式系统与容器化技术（Kubernetes、微服务治理、RPC 框架）。 ## At a glance - Posted by the employer: Not stated - First seen by OpenNash: Oct 12, 2026 - Last checked: Oct 19, 2026 - Listed for: 7 days - Location: Beijing[Apply on Tencent Holdings’s careers site →](https://careers.tencent.com/en-us/jobdesc.html?postId=2092937311057788928) ## More jobs at Tencent Holdings ### [3D动作游戏《狩》-后台开发-UE5 DS后台开发](https://jobs.opennash.com/companies/tencent-holdings/jobs/6d535d770b7d94786b5e/) Beijing ### [AI infra研发工程师(北京/深圳)](https://jobs.opennash.com/companies/tencent-holdings/jobs/eda44bea14836b2b9952/) Beijing ### [AI ⽹络集合通信库运营⼯程师](https://jobs.opennash.com/companies/tencent-holdings/jobs/59f91606e7bdc470bf0b/) Beijing ### [Aigc内容检测算法工程师（图像与视频方向）](https://jobs.opennash.com/companies/tencent-holdings/jobs/ca1cf721bb29a8df9bdf/) Beijing ### [AI智能体评测高级工程师](https://jobs.opennash.com/companies/tencent-holdings/jobs/9312d7b2c30640f3f245/) Beijing ## Similar jobs at other companies ### [AI产品经理（语音方向）](https://jobs.opennash.com/companies/geely-automobile-holdings/jobs/50f7298e66e961f962e0/) Geely Automobile Holdings · 上海市, 中国 ### [多模态大模型算法实习生（语音方向）](https://jobs.opennash.com/companies/meituan/jobs/0161454aad512617bc68/) Meituan · 北京市 +1 more 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/)