[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

# Agent Harness 开发/优化工程师-【可灵AI专项】

Beijing 

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/32532)

[OpenNash Jobs](https://jobs.opennash.com/) / [Kuaishou Technology](https://jobs.opennash.com/companies/kuaishou-technology/) / Agent Harness 开发/优化工程师-【可灵AI专项】

## Job description

负责可灵Agent Harness 的开发与优化，为视频生成及多模态创作 Agent 提供稳定、高效、可扩展的运行框架，持续提升复杂任务的完成质量、执行效率与系统可靠性。

### 包括但不限于
- 设计和优化 Agent Loop、Tool Use、上下文管理、记忆、状态管理及任务恢复等核心能力；
- 建设适用于视频创作的多阶段 Agent Workflow，优化模型、工具与生成链路之间的协同；
- 建立 Agent 评测和可观测体系，持续优化任务成功率、生成质量、延迟及成本；
- 探索 LLM 与视频生成模型在任务规划、Prompt 优化、结果反馈和自动迭代中的应用。
- 熟悉 LLM Agent 的核心机制，对任务规划、Tool Calling、上下文工程、记忆管理及多Agent 协作有实践经验；
- 对 Agent Harness 或 Agent Runtime 有系统性理解，能够处理长任务执行、状态持久化、并发调度、失败恢复及 Human-in-the-loop 等问题；
- 了解主流 LLM 的训练与推理机制，能够针对模型特性优化Prompt、工具描述、结构化输出和执行策略；
- 熟悉视频生成模型及相关技术链路，理解文生视频、图生视频、视频编辑、参考图控制和多模态理解等基本机制；

### 具备 AI-Native 的工作方式
- 善于使用 AI 编程及研究工具快速验证想法，能够通过实验、评测和数据反馈持续迭代，而非依赖经验判断。

### 加分项
- 深入理解 Transformer、Diffusion、DiT、Flow Matching 等模型原理及推理机制；
- 在 LLM、Agent、多模态理解或视频生成方向有论文、专利、开源项目等研究成果者优先；
- 有 Agent Runtime、Workflow Engine、模型平台或复杂 AI 应用落地经验；
- 对前沿技术保持敏感，具备较强的自主学习、问题定义和从不确定需求中快速形成可验证方案的能力。

## 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[Apply on Kuaishou Technology’s careers site →](https://zhaopin.kuaishou.cn/#/official/social/job-info/32532)

## More jobs at Kuaishou Technology

### [(大模型专项）多模态大模型算法工程师](https://jobs.opennash.com/companies/kuaishou-technology/jobs/98edf462c05648daadcf/)

Beijing

### [AI Agent 开发实习生（电商在线推荐引擎）](https://jobs.opennash.com/companies/kuaishou-technology/jobs/5945a85b9a833fcbb5f8/)

Beijing

### [AI Agent 策略实习生](https://jobs.opennash.com/companies/kuaishou-technology/jobs/b814e14328b750da25f6/)

Beijing

### [AI Agent算法专家](https://jobs.opennash.com/companies/kuaishou-technology/jobs/0e36be4e740de43e02ad/)

Beijing

### [AI Agent算法专家（智能创作方向）](https://jobs.opennash.com/companies/kuaishou-technology/jobs/41a78c4c892cbbd1bc50/)

Beijing

## Similar jobs at other companies

### [WeTalk-大模型应用研发工程师-（Agent Harness）](https://jobs.opennash.com/companies/tencent-holdings/jobs/fd69d7168e58482e231f/)

Tencent Holdings · Beijing

### [混元AI Agent Harness Engineer（北京/深圳））](https://jobs.opennash.com/companies/tencent-holdings/jobs/4faaed1cc2e1f8246c7b/)

Tencent Holdings · Beijing

### [AI产品经理 - Platform Governance/Agent Harness](https://jobs.opennash.com/companies/lenovo-group/jobs/b8ca692696ff0e224eb7/)

Lenovo Group · China, Beijing, 北京（Beijing）

### [优化工程师](https://jobs.opennash.com/companies/rongsheng-petrochemical/jobs/bee37b158c91e0479381/)

Rongsheng Petrochemical 

### [Agent Harness 开发工程师](https://jobs.opennash.com/companies/xiaomi/jobs/61a0564b010b70dd51eb/)

Xiaomi · 北京

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/)