CareerPlan

AI评估运营专家(交易方向) - AI数据与安全

北京Full-time2026-10-22 → 2026-11-11

Core

Build and operate an evaluation system for large models in transaction scenarios (user intent, product understanding, search, recommendation) to identify model shortcomings and drive optimization.

Role type

Senior AI evaluation operations specialist (transaction domain)

Builds

Automated evaluation systems, rubrics, and quality control mechanisms for model performance

Domain

E-commerce and platform transaction business

Deliverable

production ML models

Required skills

Large model evaluation, data operations, transaction business insight, Python, SQL, prompt engineering, rubric design, project management

Preferred skills

Experience with Vibe coding, skill optimization, tool building

Technologies

Python, SQL, Vibe coding

Responsibilities

Design evaluation schemes and standards (datasets, metrics, scoring rules); Operate full lifecycle of evaluation projects; Build automated evaluation systems; Identify model performance gaps in transaction scenarios; Collaborate with R&D to implement optimization suggestions