An early-stage startup turning complex documents into LLM-ready data.
Founding ML Researcher
Complex documents in finance, law, and healthcare remain locked behind messy formats and visual structures, making them practically useless to modern language models. As our first ML hire, you will architect the vision and extraction pipelines that convert unstructured PDFs into pristine, LLM-ready data. You will set the research direction and build foundational models from the ground up alongside a small, focused team.
What they're looking for
- 0-5 years of experience in ML research or computer vision engineering.
- Strong proficiency in Python and building production-grade ML systems.
- Deep expertise in document understanding, OCR, or layout analysis.
- Willingness to work on-site in San Francisco.