[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 · Shanghai

# TIONE-AI Infra 后台研发工程师

Shanghai 

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=2099328404741603328)

[OpenNash Jobs](https://jobs.opennash.com/) / [Tencent Holdings](https://jobs.opennash.com/companies/tencent-holdings/) / TIONE-AI Infra 后台研发工程师

## Job description

### Responsibilities
- 负责基于 Kubernetes 的大模型推理云原生平台建设，主导推理场景下的 K8s 调度、资源管理与核心插件 （Operator / CSI / CNI / 设备插件）研发，构建高弹性、多租户、异构算力统一调度的大模型推理服务平台， 支撑混元及第三方模型高效、稳定上线；

### 云原生推理平台架构
- 基于 K8s 主导 TIONE 推理平台控制面与数据面架构设计，构建高弹性、多租户的大模型推理服务，覆盖模型部署、弹性伸缩与推理调用全生命周期；

### K8s 调度与资源管理
- 深度定制 K8s 调度器（Scheduler Framework / 调度插件），实现 GPU / NPU 拓扑感知调度、优先级抢占、配额与算力池化；落地 GPU 共享虚拟化与弹性伸缩（HPA / KEDA）；

### Operator 与 CRD 开发
- 设计推理平台核心 CRD（Model / InferenceService / Deployment 等）与 Controller，基于 controller-runtime 实现生命周期管理、状态协调与故障自愈；

### 设备插件 / CSI / CNI
- 开发 GPU / NPU 设备插件（Device Plugin）完成异构算力发现与分配；落地 CSI 存储插件支撑模型与 Checkpoint 高效挂载；集成并定制 CNI（RDMA / RoCE 高性能网络）保障推理 Pod 网络与跨节点通信。 Requirements
- 本科及以上学历，计算机、软件工程、电子信息等相关专业； 3年以上后台 / 分布式系统研发或 K8s 云原生平台开发经验；
- 精通 Go 语言（核心），熟悉 C++ / Python；具备大型分布式系统与高并发、高可用服务设计与编码能力；

### 深入理解 Kubernetes 核心机制，包括但不限于
- Scheduler Framework、CRD / Operator（controller-runtime）、Admission / Webhook、Device Plugin，以及 CSI / CNI 插件原理与开发；
- 熟悉 GPU / NPU 资源管理（设备插件、共享 / 虚拟化、拓扑调度）与高性能网络（RDMA / RoCE、CNI 定制）；有主流推理框架（vLLM / TensorRT-LLM / SGLang）集成经验者优先；
- 加分项（优先条件）；
- 有大规模 K8s 集群、多租户算力平台，或存储 / 网络 / 调度器二次开发落地经验；
- 具备昇腾 / 海光 / 天数等国产 AI 芯片云原生适配与优化经验；
- 主导或深度参与开源云原生项目（Kubernetes / Volcano / KubeFlow 等）并有社区贡献。

## 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: Shanghai[Apply on Tencent Holdings’s careers site →](https://careers.tencent.com/en-us/jobdesc.html?postId=2099328404741603328)

## More jobs at Tencent Holdings

### [3A修仙RPG游戏-主策划](https://jobs.opennash.com/companies/tencent-holdings/jobs/89e9be0bc8522a47c921/)

Shanghai

### [3A动作冒险游戏-战斗主策划](https://jobs.opennash.com/companies/tencent-holdings/jobs/9a81d086671e92a54e73/)

Shanghai

### [AI Infra研发工程师-上海/北京/深圳](https://jobs.opennash.com/companies/tencent-holdings/jobs/28bf4dec4ecc0f7de3c4/)

Shanghai

### [AI 沙盒体验资深设计师（深圳/上海）](https://jobs.opennash.com/companies/tencent-holdings/jobs/e74c7711c05491c1126d/)

Shanghai

### [AI产品海外解决方案架构师](https://jobs.opennash.com/companies/tencent-holdings/jobs/568fcdcf0fbc33d4bab0/)

Shanghai

## Similar jobs at other companies

### [Servicetechnicus Infra](https://jobs.opennash.com/companies/bouygues/jobs/1171d5fcafc8a2e1c25c/)

Bouygues · ARNHEM, Netherlands

### [Cloud Infra Engineer](https://jobs.opennash.com/companies/grasim-industries/jobs/0b92dbe21b145c95e144/)

Grasim Industries · Maharashtra

### [Projectleider Ondergrondse Infra](https://jobs.opennash.com/companies/sgs/jobs/3b1ae1b162bdce2b5fa3/)

SGS · Waardenburg, GE, Netherlands

### [Sr Consultant - Infra AI](https://jobs.opennash.com/companies/microsoft/jobs/7b86651f79ff634da444/)

Microsoft · India, Telangana, Hyderabad

### [Infra Tech Support Practitioner](https://jobs.opennash.com/companies/accenture/jobs/ee7abccb8f335ac83e6e/)

Accenture 

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/)
