CareerPlanSign in

LLM大模型评估产品经理-豆包

北京💼 Full-time🗓 2026-09-28

Core

Build and maintain evaluation systems for LLM models in application scenarios to assess model value and drive optimization.

Role type

Product Manager (LLM Evaluation)

Builds

Evaluation frameworks, benchmarks, and tool platforms for LLMs

Domain

Artificial Intelligence / Large Language Models

Deliverable

production ML models

Required skills

LLM evaluation methodology, data analysis, A/B testing, cross-functional collaboration, AI Agent principles, technical report analysis

Preferred skills

English as working language

Technologies

LLM evaluation tools, benchmarking platforms

Responsibilities

Design and iterate evaluation methodologies and standards, analyze online A/B tests and user data to identify issues, produce evaluation reports, collaborate with cross-functional teams to drive model optimization

Sourced via bytedance · Listed on CareerPlan, which tracks 844,000+ jobs from 20+ sources.