1,829,202open jobs
105,335companies
276,110added this week
Browse all
Location
In office (Beijing)
Employment
Full-Time

Confirmed on the employer's own hiring board on Oct 18, 2026. First seen by Alion on Apr 3, 2026. StepFun scores B on the Alion truth index.

Overview
Company
Impact
Profile match
StepFun is a Chinese foundation model laboratory building a full range of models from language to speech, image and video. Its Step series includes very large mixture of experts models and multimodal systems, and the company releases open weights alongside commercial offerings. The laboratory was founded by a former senior Microsoft executive and is among the most heavily funded of the Chinese model startups; its models are used in Chinese consumer applications and enterprise deployments across several industries.

岗位描述

1、跟进学术界和企业界前沿的评测基准,并持续健全世界级SOTA模型的观测榜单(例如OpenAI,Anthropic等发布的SOTA模型主要在哪些榜单上证明模型能力) 例如AIME、 GPQA、HLE、Codeforces、SWE、MultiChallenge、BrowseComp、Tau-Bench、 Aider、MMMU、MathVista等。

2、开发评测基建,联合模型训练框架共同开发评测体系,保证评测体系与开源社区和头部闭源模型可对比,具备完善的对点机制,保障评测结果的可靠性。

3、日常维护评测榜单,健全评测工程体系,提高评测的效率。

4、发现模型迭代中在榜单中所反映的能力欠缺问题,分析主流SOTA模型间在评测中体现的差异点。

岗位要求

1、熟悉大模型相关研究前沿进展,了解对市面主流benchmarks,具备大模型评测经验;

2、对数据有一定的敏感度,熟知开源社区各数据渠道源,有数据处理的经验和认知;

3、具有大模型各流程或全流程的研发/客观指标评测/Agent指标评测经验、模型训练/推理框架工程经验优先;

4、具备扎实的编程基础,有优秀的工程能力; 具有NOI、ACM/ICPC等编程竞赛金牌获奖者优先;

5、有一定的相关研究经历,发表过顶级会议论文者优先;

Free account
Stop reading job ads. Get the ones that fit.
One free account turns this page into a shortlist built around your stack, your level and your pay.
Match on every job. Stack, seniority, pay and location, scored against your profile.
1,829,202 open roles. Read straight off company career pages, refreshed every day.
Unlimited applications. Every one you send is tracked in one place, on-site or on a company board.
3 tailored CVs a month. Rewritten for the exact job you are applying to. Included free.
Create a free account Continue with Google
Free forever. No card. Under a minute.

Your match

How well do you fit this role?
Two answers are enough for a real match. No account needed.
Check my fit
Answers stay in this browser until you create an account.

Recommended for you based on this role

AI/ML
Similar stack
Same company
Beijing
≈ $54k – $138k per year (Estimated) • Hybrid • Shenzhen • Guangzhou
AI/ML
AI Agents
Machine Learning
Apply
In office • Internship • Beijing
Apply
In office • Internship • Beijing
Python
C++
AI/ML
Spark
Apply
In office • Internship • Beijing
Apply
In office • Internship • Shanghai
Apply
≈ $48k – $133k per year (Estimated) • In office • Full-Time • Beijing
Apply
≈ $30k – $87k per year (Estimated) • In office • Full-Time • 2+ years exp • Beijing
Apply
≈ $48k – $133k per year (Estimated) • In office • Full-Time • Beijing
Apply
≈ $30k – $87k per year (Estimated) • In office • Full-Time • 2+ years exp • Beijing
Apply
≈ $48k – $133k per year (Estimated) • In office • Full-Time • Beijing
Apply
See all jobs
This is one of many
1,829,202 more open roles from verified company boards, updated every day.