大模型Eval评测(工程方向/产品方向)
Apply on Moonshot AI's siteTailor my resumePosted
May 17, 2026Last verified
1 h agoEmployment
Full-timeLevel
MidFunction
AI/ML EngineeringAI rolePythonGoC++SQL
Open 6 months. Roles open this long are often filled, or kept open all year. Check the date on the employer's site before you apply.
【职位介绍】
- 模型评测:设计、搭建并持续迭代大模型多维度评测框架,让模型能力“可衡量、可对比、可解释”。
- 数据驱动:与算法团队配合,把评测结论转化为数据需求,寻找可以提升模型智能的关键数据,并推动落地。
- 行业洞察:跟踪前沿论文与开源社区,第一时间把新评测维度、数据策略落地到业务中。
- 产品思维,有发现问题推动解决的能力,提升模型的能力。
【我们希望你】
必备
- Python/Go/Java/C++ 任意语言使用经验,能独立写脚本、调 API、搭小工具即可。
- 逻辑思维强,对“用数据说话”有执念,熟悉 SQL / Pandas / Jupyter 等分析工具。
- 对大模型有基础认知(用过 GPT、Claude 等),能快速理解SFT、RL 等概念。
- 有参与过大模型benchmark、evaluation等方向的工作经验。
加分
- 有 创业经验 或 开源项目贡献 或 研发背景期待转产品。
- 英语读写流畅。
Attention Head lists this role as published on Moonshot AI's own job board. Applications go to the employer.
Similar roles at other employers
- Robotics Machine Learning EngineerPantograph · San Francisco$150K–260K
- AI Training EngineerBlank Metal · Minneapolis, MNNov 20, 2026
- AI Process Automation Engineer - Security (Job 1534)DLH · Bethesda, Maryland$110K–145K
- Forward Deployed EngineerHandshake · San Francisco, CA$151K–189K
- Forward Deployed Software Engineer, Connected Warfare (Active Clearance)Anduril · Washington, District of Columbia, United States$166K–253K
All mid-level AI/ML Engineering roles →
More roles at Moonshot AI
- Nov 20, 2026
- Nov 4, 2026
- Nov 2, 2026
- Oct 20, 2026
- Sep 18, 2026
- Sep 18, 2026
- Sep 18, 2026
- Sep 4, 2026