Skip to main content
Back to all jobs

Backend Engineer at LlamaIndex

As a Backend Engineer based in San Francisco, you will take ownership of the core document infrastructure layer for LlamaCloud and LlamaParse, building systems that process millions of documents for developers globally. This high-autonomy role is perfect for a Python expert who balances the engineering rigor of top-tier tech companies with the rapid execution of a fast-moving startup environment. You will work directly with a high-caliber team to architect, deploy, and scale Kubernetes-based services that define the next generation of agentic AI workflows.

Want to apply for this role?

LlamaIndex

Jack finds you jobs at companies like LlamaIndex. Talk to Jack to get considered for roles that fit what you're great at.

Location

San Francisco, United States

Compensation

Not Disclosed + Equity

Company

LlamaIndex

Talk to Jack

About this role

Role overview

Join a high-caliber team at LlamaIndex building core services like LlamaCloud and LlamaParse. You will own the backend lifecycle for tools powering AI agentic workflows at scale. This role focuses on designing robust APIs and scaling Kubernetes-based infrastructure to handle millions of documents for a massive global developer community.

About the company

LlamaIndex is building the document infrastructure for AI agents. It contains a best-in-class agentic document processing engine to parse the most complex documents and translate them into formats that humans and AI can use. It also contains a variety of tools at the semantic layer (extraction/search) and agentic layer (workflows) to enable knowledge work over documents.

What you'll do

What you will do

  • Design, develop, and maintain high-performance Python-based APIs (REST, GraphQL, or gRPC) that serve as the foundation for LlamaCloud and LlamaParse.
  • Architect and manage Kubernetes-based deployments across AWS/GCP, ensuring the scalability and reliability of systems processing millions of documents.
  • Collaborate with a lean engineering team to ship end-to-end features, from service architecture to CI/CD automation via GitHub Actions.

Who you are

Who this is a fit for

  • Has 4+ years of production experience in Python, demonstrating engineering rigor from top-tier tech firms combined with the velocity of early-stage startups.
  • Possesses deep expertise in Kubernetes, including deploying, scaling, and debugging complex containerized environments in production settings.
  • Demonstrates a proven track record of shipping independently and thriving in fast-paced environments without the need for heavy management process or overhead.

Why this role

Why this role is remarkable

  • Scale massive impact with over 25 million monthly downloads on the open-source library, reaching the heart of the global AI developer ecosystem.
  • Join a small, high-autonomy Series A team where you shape architectural decisions for critical AI infrastructure rather than just executing pre-defined tickets.
  • Work at the cutting edge of AI agentic workflows, building the document processing layer that powers the world's most advanced LLM applications.

Jack & Jill

How Jack & Jill work together

Jack
I get to know what you’re great at, then find roles you’d never find yourself.
Jill
I recruit from Jack’s network and make the intro when I spot a great match.
Thumbnail for Meet Jack

Jack gets to know what you're great at and what you want next, then searches 15 million jobs daily and helps you discover roles at companies like this.

Meet Jack

What happens next?

Jack’s an AI agent for job searching and career coaching. He works for you.

Jill is the AI recruiter working for the company. She recruits from Jack’s network.

If your profile’s a match and LlamaIndex wants to meet, Jill will make the intro. In the meantime, Jack will send you excellent alternatives.

Learn about Jack

Ready to find your next role?

Talk to Jack for 10 minutes and see your first matches.