About the job

Job Description

Job Summary

Zendesk’s people have one goal in mind: to make Customer Experience better. Our products help more than 145,000 global brands (AirBnb, Uber, JetBrains, Slack, among others) make their billions of customers happy, every day.

Our team is dedicated to providing a robust full-text search experience for our customers across multiple channels; including help centers and agentic RAG (retrieval-augmented-generation) bots. In collaboration with ML engineers and scientists, we deliver high-quality AI products leveraging the latest tools and techniques, and serve them at a scale that most companies can only dream of. We’re passionate about empowering end-users to find what they’re looking for, and helping our customers get the most out of their knowledge base.

We’re looking for a Staff Machine Learning Engineer to join our team and play a key role in leveling up the search platform powering Zendesk!

What You’ll Be Doing

• Delivering AI-powered capabilities to our customers at Zendesk scale using latest LLM technologies
• Working closely with Product Management, ML Scientists and fellow Engineers both within the team and across the company to define feature scope and implementation strategies, using ML technology
• Mentoring junior team members, as well as pairing with more experienced colleagues to foster mutual learning
• Supporting our deployed services to ensure a high level of stability and reliability
• Writing clean and maintainable code to meet the team’s delivery commitments
• Contributing to discussions regarding technical design and best practices
• Here some of the challenges you will be working on:
  • How do we expand our RAG platform to handle new use cases?
  • How do we integrate and improve hybrid search solutions combining vector embeddings and keyword-base retrieval?
  • How do we enhance the ranking of search results?
  • How do we optimize our indexing pipeline for speed and cost-efficiency?
  • How do we best provide a retrieval platform across multiple channels?
  • How do we make the best use of rapidly evolving LLM technologies?
  • And many more!