About the job
Zoom is building the next generation of AI Companion, powered by Agentic Retrieval — a unified intelligence layer that enables AI agents to securely search, reason over, and act on enterprise knowledge at scale. In this role, you’ll design and develop the core retrieval and reasoning systems driving AI-powered workflows across meetings, chat, docs, and enterprise apps. This is a high-impact opportunity to shape Zoom’s AI foundation and advance how enterprises access and use knowledge.
Responsibilities
Designing and building scalable retrieval systems using vector and semantic search for unstructured data, hybrid keyword-embedding search, enterprise data analytics, and graph-based reasoning.
Designing and optimize Retrieval-Augmented Generation (RAG) pipelines for multi-step, tool-using AI agents.
Building indexing pipelines that transform heterogeneous enterprise data into unified retrieval-ready representations.
Developing ranking, relevance modeling, and evaluation frameworks to improve answer quality and grounding.
Working on permission-aware retrieval to ensure secure, multi-tenant isolation and fine-grained access control.
Partnering closely with product, infrastructure, and applied research teams to ship production-grade AI capabilities.
Qualifications
Minimum
Master’s degree or higher in Computer Science, Artificial Intelligence, Machine Learning, Distributed Systems, or a related field.
5+ years of experience in machine learning, search infrastructure, information retrieval, distributed systems, or related areas.
Demonstrate hands-on experience building and operating large-scale search, recommendation, or data platforms in production environments.
Possess understanding of:Information retrieval, Structured query systems, Knowledge graph or graph database concepts
Have experience building or integrating RAG systems and LLM-based applications in production.
Possess proficiency in one or more of: Python, Go, Java, C#, or C++.
Have experience with modern ML frameworks (e.g., PyTorch, TensorFlow) and vector databases or search engines.
Preferred
Have experience working with enterprise data systems or multi-tenant SaaS environments is a plus.