Jobs

Find AI roles by technical focus, location, and employment type.

Technical focusAll
Technical focus

Select one or more; matches any selected direction.

Back to jobs

研究型实习生-自进化智能体系统基础研究

Location
Beijing
Employment type
Intern
Agent

Responsibilities

智能体正从“回答一次请求的工具”转向“长期运行的进程”,经验必然累积、环境必然变化。自我演化的两条路线——训练期内化(经验写入权重)与运行期外化(经验存入外置库、技能库)——已相继得到验证,但二者共享同一个系统级缺口:经验没有生命周期、没有账本、没有预算、没有属主。本项目面向这一空白,构建经验的放置、治理、一致性与成本核算基础设施。 以“经验是一等系统资源”为核心命题,将经验建模为“捕获 → 验证 → 沉淀 → 执行 → 退役”五阶段生命周期,演化开销可计量且受预算约束。以 Coding Agent 为研究场景,部署四项任务: 1. 存储层级与放置:建立上下文→外置库→编译制品→模型权重的四级谱系及固化、编译、内化转换机制。 2. 可验证性与沉淀:验证强度决定写入深度。 3. 经验一致性:失效低成本检测、重算或废弃决策及依赖图传播。 4. 双平面设施:演化与服务共驻的干扰隔离与不停机在线演化。

Requirements

1、计算机科学、人工智能、电子工程或相关专业博士; 2、精通 PyTorch 框架,具备良好的代码工程能力; 3、熟悉分布式系统、大模型推理架构或Agent记忆机制; 4、深入理解SFT、RL等偏好对齐算法及Off-Policy/On-Policy蒸馏机制; 5、在 OSDI / SOSP / EuroSys / MLSys / NeurIPS / ICML / ICLR 等顶级会议发表过相关论文者优先; 6、具备优秀的科研创新能力、问题抽象能力与跨团队协作精神。

Who this role is for

在校博士

Company overview

Leave with unsaved changes?

Save your drafts before leaving, or discard only the changes made since the last save.

Get help

Contact Relia for help with job applications, job posting, or reviews.

Contact Reliadylan@relia.ai
Email us

You can also copy the address and contact us from your usual email service.

Job applications
Use the application method listed on the job. Contact us if a link or email does not work, or if you need help applying.
Job posting
Contact us for help registering a company, posting a job, or preparing a job listing for review.
Reviews
Contact us with questions about recruiting eligibility, job status, or review feedback.

Please describe the issue and include the job link or company name. Include an application reference if available.

Assisted listings and submissions still require verification and review.