Overview
Frontend owner for a document intelligence team, building production UIs for reviewing documents, correcting extractions, designing schemas, and monitoring evaluation results.
What you'll do
- Build document review interfaces for PDFs and images with navigation and overlays.
- Implement human-in-the-loop correction workflows for field edits and approve/reject queues.
- Develop tools to design, test, and version structured extraction schemas.
- Create internal evaluation and observability dashboards for accuracy, latency, and cost.
- Handle streaming and long-running states including partial results and resumable sessions.
- Own frontend performance for large documents using virtualization, canvas rendering, and lazy loading.
- Partner on API contracts with backend and applied AI engineers.
What you'll need
- 4–5 years building production frontend applications with strong ownership.
- React expertise including hooks, rendering behavior, state management, and performance profiling.
- Strong TypeScript skills using the type system to prevent bad states.
- Command of browser fundamentals (layout, events, memory, rendering) and comfort with Canvas or SVG.
- Experience with complex, data-dense product surfaces like dashboards, editors, or review tools.
- API integration instincts for async state, caching, polling/streaming, and error/retry handling.
- Design sensibility to ship clean UI from rough direction.
Nice to have
- Experience with PDF rendering in the browser (PDF.js or equivalent) or annotation/labelling tools.
- Familiarity with WebSockets, SSE, or other streaming transports.
- Exposure to AI/ML product surfaces such as human-in-the-loop review and eval tooling.
- Comfort working in a Python or Go backend when needed.
- Design systems ownership and strong accessibility practice.
Details
- Frontend owner for the document intelligence team.
Read the full description and apply on the company’s own careers page.
