Senior RAG Engineer for AI Knowledge Platform (Remote)

Socket.dev; Seattle (WA); Hybrid; USD 200,000 - 275,000; Full time

Job summary

Zoom Communications, Inc. is seeking a backend/distributed systems engineer to design and implement a scalable RAG system for real-time Q&A on internal content. You will build ingestion pipelines, APIs, and backend services, collaborating with ML/NLP teams to improve embedding models and search quality.

You will ensure reliability and low latency across the data retrieval stack while supporting a multi-tenant architecture and high-throughput workloads in a structured hybrid/WFH setup.

Qualifications

• Master's degree or foreign equivalent required.

Responsibilities

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

Skills

Backend systems

Distributed databases

Cassandra

ScyllaDB

Postgres

ElasticSearch

Redis

Kafka

RabbitMQ

Docker

Kubernetes

AWS

Multi-tenant

Real-time Q&A

Education

Master's degree in Computer Science or related field

Tools

None

Job description

Zoom Communications, Inc. is seeking a backend/distributed systems engineer to design and implement a scalable RAG system for real-time Q&A on internal content. You will build ingestion pipelines, APIs, and backend services, collaborating with ML/NLP teams to improve embedding models and search quality.

You will ensure reliability and low latency across the data retrieval stack while supporting a multi-tenant architecture and high-throughput workloads in a structured hybrid/WFH setup.