Join the LlamaAgents early access waitlist!

Open Source Engineer, AI Frameworks

Join us and help shape the future of AI by architecting next-generation knowledge systems.

Apply now

Location

San Francisco

Employment Type

FullTime

Location Type

Hybrid

Department

Engineering

Join us and help shape the future of AI by redefining document workflows with AI agents.

About The Role

We're seeking an Open Source Engineer to help build and evolve our cutting-edge AI framework that empowers developers to create sophisticated LLM-powered applications. The selected candidate would ideally work directly on either our Python and Typescript frameworks (or both!). As a Founding Open Source Engineer, you'll be instrumental in developing and maintaining our Python libraries focused on LLM applications, embeddings, retrievers, and intelligent agent frameworks.

Responsibilities

  • Design intuitive, powerful interfaces and abstractions that make complex AI capabilities accessible to developers. This includes:

    • agent capabilities and reasoning

    • agent memory

    • retrieval algorithms

    • LLM response strategies

    • product-facing SDKs using LlamaCloud

  • Maintain open-source repos, including

    • Responding to and handling Github issues and pull-requests

    • Writing and refining documentation and examples

    • Collaborating with users across the world

    • contributing an extensive CICD system that runs across 500+ python packages

Qualifications

  • 3+ years of software engineering experience

  • Proficient in Python, including

    • dependency management (poetry, uv, etc.)

    • utilizing recent python linters (ruff, mypy, etc.)

    • Using pydantic for validation and serialization

    • Servers like FastAPI and Flask

    • Frontend frameworks like Streamlit, Gradio, or Reflex

  • Passion for open-source development

  • Contributed to or managed prominent open-source projects

Preferred Qualifications

  • Understanding of NLP, ML, and LLM architectures

  • Portfolio demonstrating experience implementing latest generative-AI patterns and algorithms

  • Experience with docker and kubernetes

Location

Hybrid in San Francisco, CA preferred. Remote available.

What We Offer

  • Be a member of an innovative AI infrastructure team

  • Work on challenging, meaningful technical problems

  • Significant creative and technical autonomy

  • Opportunity to shape an open-source project with global impact

Why Join Us?

  • Impactful Mission: Work on innovative AI products that redefine how knowledge is accessed and utilized.

  • Collaborative Team: Join a team of passionate individuals committed to pushing the boundaries of technology.

  • Growth Opportunities: Be at the forefront of the AI revolution, with ample opportunities to grow alongside our scaling organization.

Additional Benefits

  • Competitive base salary and equity compensation

  • Comprehensive medical/dental/vision coverage for you and your family

  • Unlimited paid time off policy

  • Daily catered lunch and snacks in the San Francisco office

Pursuant to the San Francisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.

LlamaIndex does not accept unsolicited agency resumes. Please do not forward resumes to our jobs alias, employees, or any other organization location. LlamaIndex is not responsible for any fees related to unsolicited resumes.

Values We Look For

01

Unwavering Integrity with Purpose

We operate with complete honesty and stay true to our mission.

02

Resourceful Innovation

We adapt quickly, solve creatively, and thrive in ambiguity.

03

Exceptional Drive & Execution

We think strategically and deliver results with urgency.

04

Elevate & Empower

We share knowledge, build trust, and help teammates excel.

05

Deep Expertise

We value and cultivate deep domain knowledge. True innovation comes from mastering our craft and understanding the nuances of our field.

Start building your first document agent today

LlamaIndex gets you from raw data to real automation — fast.