Join us and help shape the future of AI by redefining document workflows with AI agents.
We're seeking an Agent Engineer to join LlamaIndex, where you'll contribute to cutting-edge AI frameworks that empower developers worldwide to create Document Agents and RAG applications. Your work will directly impact thousands of developers and shape how the industry builds with LLMs and knowledge bases.
Collaborative Innovation: We work in a high-trust environment where engineers own their ideas from conception to release. We expect autonomy and offer the same to peers—great ideas can come from anywhere.
Community-Driven Excellence: Our success is measured by developer impact, from open-source developers building prototypes to enterprise customers running production AI systems. We iterate based on real-world feedback across the entire spectrum.
Continuous Learning: We stay at the forefront of AI research and technology. The field moves fast, and so do we—experimentation and learning are part of the job.
Radical Transparency: Open-source is more than code - it's a commitment to shared knowledge
As an Agent Engineer at LlamaIndex, you'll wear two hats:
Open Source Innovation (60-70%)
Design and build core agent capabilities, retrieval algorithms, and document processing features that thousands of developers rely on daily. You'll push the boundaries of what's possible with LLM agents while maintaining the elegant, intuitive APIs LlamaIndex is known for.
Product Bridge (30-40%)
Work closely with our platform teams to translate open-source innovations into production-ready APIs and services via LlamaCloud. You'll ensure seamless developer experiences across both worlds, bringing learnings from open-source experimentation to productized features.
Building Core Agent Tech:
Develop and iterate rapidly on agentic reasoning systems, memory architectures, and retrieval pipelines that handle real-world document complexity
Ability to reason about LLM behavior, retrieval quality, and system design from first principles. This means building focused, high-quality tools rather than general-purpose wrappers.
Building with the community. This means helping to manage community interactions and feedback over Github and Discord.
Bridging Open Source & Product:
Shape the evolution of LlamaCloud SDKs by bringing learnings from open-source experimentation to production APIs
Collaborate with platform teams to ensure feature parity and smooth migration paths between OSS and managed services
Translate community feedback and use cases into actionable product requirements
3+ years of software engineering experience with production Python systems
Expert-level Python: modern tooling (uv, ruff, mypy), Pydantic, FastAPI/Flask
Hands-on experience building LLM-powered applications (production or personal projects), using both existing AI frameworks and from-scratch
Solid understanding of RAG patterns, embeddings, vector databases, and semantic search. All with existing AI frameworks and from-scratch
Active open-source contributor with strong technical writing skills
First-principles thinking: you build precise, well-scoped tools and understand why abstractions exist, not just how to use them
Deep knowledge of LLM architectures and internals (transformers, attention mechanisms, training/fine-tuning)
Built production agent systems with multi-step reasoning, tool use, or planning
Meaningful contributions to popular AI/ML open-source projects
Experience with Docker/Kubernetes, distributed systems, or API design
Active in AI research community (papers, blog posts, talks)
Hybrid in San Francisco, CA preferred. Remote available.
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
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.
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.
If an employer mentions a salary or salary range on their job, we display it as an "Employer Estimate". If a job has no salary data, Rise displays an estimate if available.
Senior Software Engineer (remote, US) to build full-stack, workflow-driven data discovery and access systems that balance usability with governance.
Experienced Full Stack .NET Developer wanted to support website builds, integrations and mobile app maintenance for a growing Kansas City marketing agency while working remotely with local proximity to Kansas City or Chattanooga.
The Athletic seeks a graphics-focused journalist-engineer to develop and maintain interactive publishing platforms and tooling that deliver performant visual journalism across apps and web.
Be the subject-matter expert for Lumafield’s computer vision and ML solutions, developing, deploying, and supporting CV/ML features for customers while collaborating closely with product and engineering teams.
A Jobgether partner seeks a remote Software Engineer in Test to develop API and infrastructure automation frameworks, integrate testing into CI/CD pipelines, and mentor engineering teams to improve software reliability.
Work remotely as a Full Stack Developer (JavaScript/React/Node.js) building scalable, secure SaaS products that protect user data and automate enterprise compliance.
Join Anduril's Maneuver Dominance team as a Senior Robotics Software Engineer to build and scale multi-asset autonomy and mission systems that operate in real-world, deployed environments.
NVIDIA’s 12-week Ignite internship provides first- and second-year undergraduates immersive, on-site software engineering experience across AI, embedded systems, drivers, and systems software at the Santa Clara campus.
Assembled is hiring a Software Engineer to design and build autonomous AI agents and the LLM infrastructure that powers scalable, real-world customer support solutions.
Own and resolve the most complex L4 escalations for a leading AI storage platform, driving tooling, automation, and architectural recommendations to improve reliability and MTTR.
A mid-level software engineer role focused on Java/Angular web and mobile features, delivering customer-facing solutions and modernizing legacy systems in an agile team.
Senior Software Engineer (Computer Vision) to architect and implement real-time .NET systems and camera-driven CV/AR features for healthtech applications at Inmar.
Remote .NET Developer/Product Specialist to support Maine Department of Labor's PFML system using C#, .NET, PostgreSQL and FAST configuration expertise.