Documentation Engineer
US$180,000 – US$250,000 / yr base salary
Posted 13 Oct 2026
BranchFactor Summary
The original posting with the fluff stripped out
- Management level
- Individual contributor
- Employment
- Remote
- Contract
- Full-time
| Base salary | US$180,000 – US$250,000 / yr |
|---|
About LanceDB
AI advances at the speed of its research, and research moves at the speed of its data. LanceDB is the AI-native Multimodal Lakehouse: one system where a researcher curates petabytes of video, audio, and every signal derived from them with a few lines of Python, and the next training run starts as fast as the next idea. Customers like Runway, Midjourney, and Netflix build the future of AI on LanceDB, from frontier and world models to robots and autonomous vehicles.
About the Role
As the Documentation Engineer at LanceDB, you will make Lance and LanceDB easier to understand, adopt, and use in production. You'll work at the intersection of engineering, technical writing, and developer experience, turning complex data infrastructure concepts into clear explanations and working examples.
You'll partner closely with engineering, product, and our open-source community to document new features, build runnable examples, and keep guidance accurate as the product evolves. This role will own documentation as part of the product, with a particular emphasis on content that both developers and AI agents can discover, understand, and use reliably, while also building the tooling that keeps it accurate.
This is an opportunity to define how documentation supports a growing ecosystem of AI-assisted development and have a meaningful impact on how developers and AI agents learn and build with LanceDB.
What You'll Do
-
Core documentation: Create and maintain quickstarts, tutorials, conceptual guides, API references, and troubleshooting documentation for Lance and LanceDB.
-
Documentation for AI agents: Design documentation agents can use reliably, including structured API descriptions, explicit prerequisites, complete examples, and clear error and recovery guidance. Evaluate it through agent-driven tasks to find where missing context or ambiguous instructions prevent agents from completing workflows correctly.
-
Runnable examples: Build examples and sample applications that demonstrate workflows such as data ingestion, vector search, filtering, indexing, and multimodal data management.
-
AI-assisted workflows: Use AI coding assistants and other AI tools to research the codebase, draft and revise content, generate examples, and automate maintenance, verifying outputs against product behavior and tested code.
-
Documentation tooling: Maintain documentation tooling and automate checks for code examples, API references, links, and content quality.