LlamaIndex

Full-Stack Product Engineer

LlamaIndex
Apply
9 months ago
San Francisco, CA, USAMid Level
H1B Sponsor

Base Salary

$150k - $230k/yr

Responsibilities

  • Build frontend and full-stack functionality for the managed applications and SaaS offering.
  • Develop frontend features using Next.js, shadcn, and react-query.
  • Develop backend and infrastructure components using Python, Node.js, Kubernetes, Docker, Terraform, cloud services, and databases.
  • Develop, maintain, and provide education for open-source Python and TypeScript frameworks.
  • Work with prospects and customers to build proof-of-concept and production solutions.
  • Collaborate with product and design and help develop and iterate the product roadmap.

Requirements

  • At least 2 years of experience.
  • Experience shipping web applications or building new product features from scratch, including taking prototypes to production for end users quickly.
  • Experience shipping AI/LLM-native applications across user experience and core algorithms.
  • Experience iterating rapidly with customers, translating feedback into features, and participating in proactive user discovery.
  • Experience working with product and design, including proactively scoping and designing features.
  • Experience shipping applications that scaled to millions of users.
  • Machine learning and natural language processing experience is a plus.

Benefits

  • Hybrid-friendly work arrangement based out of the downtown San Francisco office
  • Competitive base salary and equity compensation
  • Medical, dental, and vision coverage for employees and families
  • Unlimited paid time off
  • Daily catered lunch and snacks in the San Francisco office
LlamaIndex

About LlamaIndex

11-50 employees

LlamaParse is the most accurate agentic OCR platform for production AI — purpose-built for the documents agents actually encounter in the real world. Unlike general-purpose models that guess at structure, LlamaParse is engineered for complex layouts, dense tables, handwritten annotations, and scanned pages. Every page is automatically routed to the optimal model, so accuracy and cost are optimized without manual configuration. Trusted by teams at Lovable, 8am, Tabs, KPMG, and others running document-intensive workflows across legal, finance, healthcare, and more.