Redefining document workflows with AI agents by pushing the boundaries of document understanding.
Requirements
Strong software engineering background with deep expertise in Typescript
Experience with document processing technologies (e.g., PDF parsing, OCR, layout analysis)
Strong understanding of modern AI/ML techniques, particularly in document understanding and NLP
Experience with production API design and implementation
Willingness to read file format specification documents and RFCs
Strong expertise in Python
Experience with computer vision or document understanding models
Responsibilities
Design and implement advanced document parsing pipelines that handle complex PDFs, PowerPoints, Word documents, spreadsheets, and any other kind of files
Develop and optimize machine learning models for document structure understanding, table extraction, and layout analysis
Build and maintain robust APIs and infrastructure to support high-volume document processing
Collaborate with the broader AI team to improve RAG pipeline integration and document preprocessing
Drive technical decisions while balancing speed, quality, and maintainability
Contribute to both our open-source framework and enterprise offering
Other
3+ years of experience
Track record of executing with high intensity in fast-paced environments
Background in technical product development at fast-growing startups
Proven track record of shipping production ML systems
Hybrid-friendly culture based out of our downtown San Francisco office
