Job Description
- Design LLM-based pipelines to identify and summarize customer pain points from textual data
- Develop summarization, clustering, and topic modeling approaches to group recurring themes
- Apply prompt engineering, retrieval-augmented generation (RAG), and embedding search to improve model accuracy and relevance
- Use machine learning methods in concert with LLM
- Build and maintain data pipelines to ingest and clean data from diverse sources
- Ensure data quality, scalability, and compliance with internal governance and data privacy policies
- Productionize models and integrate outputs with downstream systems and dashboards
- Design and build interactive visualizations (in JavaScript) that make model outputs accessible and actionable
- Partner with Insights teams to create data stories and presentations that influence business strategy
- Ability to derive insight from data, visualize it appropriately and influence others to drive outcomes
- MSc or PhD in Computer Science, Data Science, Statistics, or a related field
- 4+ years of experience in machine learning, NLP, or data-driven product development
- Strong coding proficiency in Python (Pandas, PyTorch, Hugging Face, LangChain, umap, hdbscan, etc.)
- Strong experience with front end development with JavaScript and data visualization libraries (e.g. D3.js)
- Experience deploying and managing machine learning services in containerized environments using Docker and Kubernetes
- Deep understanding of vector databases, semantic search, and embedding-based retrieval systems
- Proficient with GitHub and modern version control best practices (e.g. code reviews, CI/CD workflows)
- Proven experience working with large-scale unstructured text data
At eBay, we're more than a global ecommerce leader — we’re changing the way the world shops and sells. Our platform empowers millions of buyers and sellers in more than 190 markets around the world. We’re committed to pushing boundaries and leaving our mark as we reinvent the future of ecommerce for enthusiasts.
Our customers are our compass, authenticity thrives, bold ideas are welcome, and everyone can bring their unique selves to work — every day. We're in this together, sustaining the future of our customers, our company, and our planet.
Join a team of passionate thinkers, innovators, and dreamers — and help us connect people and build communities to create economic opportunity for all.
About the role and the team:
eBay’s India Analytics Center is a vital hub within our global analytics organization, bringing together a team of 75+ talented business analysts, data scientists, and machine learning engineers. We partner across key business areas — including Customer Service, Finance, Category Management, Seller Experience, Shipping & Logistics, and Monetization — to deliver data-driven insights that shape eBay’s strategy and customer experience.
We’re looking for a Data Science Analyst to join our Customer Service Science team, with deep expertise in Large Language Models (LLMs) and natural language understanding (NLU). In this role, you’ll help evolve Nexus, our intelligent AI-powered system that analyzes, summarizes, and surfaces customer pain points from massive volumes of unstructured data — spanning eBay’s listing posts, customer support conversations, surveys, and social media feedback.
As part of this team, you’ll play a key role in transforming how eBay listens to and acts on customer feedback. You’ll work at the intersection of AI research, data science, and business intelligence, collaborating closely with product managers, UX researchers, engineers, and analysts. You’ll design and deploy models that turn qualitative feedback into actionable insights and integrate seamlessly with a JavaScript-based front end that empowers business and product stakeholders to explore and act on customer sentiment in real time.
What you will accomplish:
- Modeling & NLP Development
- Design LLM-based pipelines (e.g., using Langchain frameworks) to identify and summarize customer pain points from textual data.
- Develop summarization, clustering, and topic modeling approaches to group recurring themes across markets and product lines.
- Apply prompt engineering, retrieval-augmented generation (RAG), and embedding search to improve model accuracy and relevance.
- Use machine learning methods in concert with LLM.
- Data Engineering & Processing
- Build and maintain data pipelines to ingest and clean data from diverse sources (e.g., surveys, customer support tickets, product reviews, social media, and CRM systems).
- Ensure data quality, scalability, and compliance with internal governance and data privacy policies.
- Productionize models and integrate outputs with downstream systems and dashboards.
- Insights Delivery & Visualization
- Design and build interactive visualizations (in JavaScript) that make model outputs accessible and actionable for non-technical stakeholders.
- Partner with Insights teams to create data stories and presentations that influence business strategy using clear, human-readable summaries of complex findings.
What you will bring:
- Ability to derive insight from data, visualize it appropriately and influence others to drive outcomes
- MSc or PhD in Computer Science, Data Science, Statistics, or a related field.
- 4+ years of experience in machine learning, NLP, or data-driven product development.
- Strong coding proficiency in Python (Pandas, PyTorch, Hugging Face, LangChain, umap, hdbscan, etc.)
- Strong experience with front end development with JavaScript and data visualization libraries (e.g. D3.js)
- Experience deploying and managing machine learning services in containerized environments using Docker and Kubernetes.
- Deep understanding of vector databases, semantic search, and embedding-based retrieval systems.
- Proficient with GitHub and modern version control best practices (e.g. code reviews, CI/CD workflows).
- Proven experience working with large-scale unstructured text data.
