Agent数据与评测Leader(Coze方向)-Dev Infra
Core
Building and managing evaluation systems for programming, Claw, and vertical Agent scenarios to support effect assessment, issue localization, and iteration loops.
Role type
Senior IC/Lead Dev Infra Engineer (Agent Evaluation)
Builds
Evaluation pipelines, data analysis chains, and automated evaluation capabilities for large models and Agents.
Domain
Artificial Intelligence / Large Language Models / Agent Development
Deliverable
production ML models
Required skills
Python, Go, C++, data analysis, engineering, team management, benchmark design, data synthesis, data governance
Preferred skills
Agent development experience, complex scenario evaluation, academic publications
Responsibilities
Design and collect high-quality evaluation data, collaborate with business and product teams on effect iteration, lead the 0-1 setup of evaluation infrastructure.
Seniority
Senior, hands-on IC with management responsibilities