Search Infrastructure Engineer

Zoom • Seattle, WA

1d • Hybrid

About The Position

We’re building the next-generation AI-native knowledge platform to help organizations easily access and retrieve internal knowledge using the power of LLMs. You’ll join a fast-moving engineering team to build scalable, secure, and intelligent Retrieval-Augmented Generation (RAG) infrastructure — powering enterprise search, AI assistants, and knowledge discovery experiences.
About the Team You’ll collaborate with world-class engineers, designers, and product thinkers to define what "AI-powered search" really means in the enterprise. As a core engineer on this team, you'll work across real-time document pipelines, vector databases, and permission-aware retrieval to push the boundaries of applied LLM systems at scale.

Requirements

• Have a Bachelor's degree and 4+ years of experience in backend or distributed systems engineering
• Have a productivity mindset with experience using AI tools effectively
• Have experience designing and operating large-scale data ingestion pipelines (message queues, vector stores, Temporal, Elasticsearch etc.)
• Demonstrate a track record of building highly available, multi-tenant backend services
• Have experience with document-level permission modeling and secure data handling
• Possess with cloud-native tools such as Docker, Kubernetes, and AWS

Nice To Haves

• Have experience in Go is a bonus
• Have experience integrating with SaaS platforms (Google Workspace, Microsoft 365, Slack, etc.)

Responsibilities

• Designing and implementing a scalable RAG system for real-time Q&A across internal content (meetings, messages, documents, whiteboards, videos, etc.).
• Building robust ingestion and indexing pipelines for semi-structured data sources with fine-grained, permission-aware access control.
• Developing APIs and backend systems to enable efficient querying, retrieval, and ranking.
• Collaborating with ML/NLP engineers to iterate on embedding models and improve search quality.
• Ensuring reliability, low latency, and scalability across the entire data retrieval and augmentation stack.
• Monitoring system performance and optimize for high-throughput, low-latency workloads under real-world load.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees