AI Agent Data Analysis / Data
招聘时间
即日起 至 2026-12-31
招聘单位
eBay
所在地区
上海
工作地点
上海市/上海市/黄浦区 来福士
学历要求
本科
实习时长
每周4天，每天6小时
职责描述
About the Role
We are looking for an AI Agent Data Analysis / Data Engineering Intern to support the development and optimization of AI-powered agent systems in a cross-border e-commerce environment.
In this role, you will work closely with engineers and business stakeholders to build the data foundation, observability, and evaluation framework for AI Agents. Rather than focusing only on dashboards, you will help create a full data loop for AI applications: logging, data pipelines, Hive-based analysis, evaluation datasets, and performance insights.
This is a strong fit for candidates who are interested in the intersection of LLM applications, data engineering, and product analytics.
What You’ll Do
● Design and improve logging schemas for AI Agent execution, including request, response, tool calls, latency, status, and error tracking
● Build and maintain Hive-based data pipelines for raw logs, cleaned datasets, and aggregated metrics
● Develop SQL/Python workflows to support AI Agent performance analysis, including success rate, failure reasons, latency breakdown, fallback rate, and workflow-level metrics
● Create and maintain evaluation datasets / golden datasets from real business cases for offline analysis and model or prompt comparison
● Help define key metrics and monitoring views for AI Agent quality and operational health
● Analyze production and experiment data to identify:
○ where failures happen
○ which scenarios have the highest impact
○ whether prompt/workflow changes improve outcomes
● Document data definitions, metric logic, and analysis methodology for ongoing team use
What We’re Looking For
● Currently pursuing a Bachelor’s or Master’s degree in Computer Science, Data Science, Statistics, Information Systems, or a related field
● Strong SQL skills, especially for analytical queries and data transformation
● Familiarity with Python for data processing, scripting, or analysis
● Basic understanding of data engineering concepts, such as ETL, schema design, data quality checks, and batch pipelines
● Good analytical thinking: able to go beyond reporting numbers and explain why something is happening
● Strong communication skills and the ability to work with both engineering and business teams
● Good written English for documentation and analysis summaries
Preferred Qualifications
● Experience with Hive, Spark SQL, or other big data query engines
● Familiarity with LLM / AI Agent / prompt evaluation concepts
● Experience working with application logs, event tracking, or observability data
● Understanding of backend systems, APIs, asynchronous workflows, or microservice-based architectures
● Experience building internal analytics tools, dashboards, or data reports
● Exposure to CRM, customer support, marketing, or e-commerce data is a plus
We are looking for an AI Agent Data Analysis / Data Engineering Intern to support the development and optimization of AI-powered agent systems in a cross-border e-commerce environment.
In this role, you will work closely with engineers and business stakeholders to build the data foundation, observability, and evaluation framework for AI Agents. Rather than focusing only on dashboards, you will help create a full data loop for AI applications: logging, data pipelines, Hive-based analysis, evaluation datasets, and performance insights.
This is a strong fit for candidates who are interested in the intersection of LLM applications, data engineering, and product analytics.
What You’ll Do
● Design and improve logging schemas for AI Agent execution, including request, response, tool calls, latency, status, and error tracking
● Build and maintain Hive-based data pipelines for raw logs, cleaned datasets, and aggregated metrics
● Develop SQL/Python workflows to support AI Agent performance analysis, including success rate, failure reasons, latency breakdown, fallback rate, and workflow-level metrics
● Create and maintain evaluation datasets / golden datasets from real business cases for offline analysis and model or prompt comparison
● Help define key metrics and monitoring views for AI Agent quality and operational health
● Analyze production and experiment data to identify:
○ where failures happen
○ which scenarios have the highest impact
○ whether prompt/workflow changes improve outcomes
● Document data definitions, metric logic, and analysis methodology for ongoing team use
What We’re Looking For
● Currently pursuing a Bachelor’s or Master’s degree in Computer Science, Data Science, Statistics, Information Systems, or a related field
● Strong SQL skills, especially for analytical queries and data transformation
● Familiarity with Python for data processing, scripting, or analysis
● Basic understanding of data engineering concepts, such as ETL, schema design, data quality checks, and batch pipelines
● Good analytical thinking: able to go beyond reporting numbers and explain why something is happening
● Strong communication skills and the ability to work with both engineering and business teams
● Good written English for documentation and analysis summaries
Preferred Qualifications
● Experience with Hive, Spark SQL, or other big data query engines
● Familiarity with LLM / AI Agent / prompt evaluation concepts
● Experience working with application logs, event tracking, or observability data
● Understanding of backend systems, APIs, asynchronous workflows, or microservice-based architectures
● Experience building internal analytics tools, dashboards, or data reports
● Exposure to CRM, customer support, marketing, or e-commerce data is a plus
