A rapidly growing AI company needs to build and optimize the core infrastructure for its document processing API, which trains vision models and integrates LLMs to read unstructured documents at scale for hundreds of companies.
Requirements
- 2+ years of experience building real-world applications and integrating LLMs into production systems.
- Exceptional proficiency in Python.
- A quantitative approach to building products, with the ability to debug, experiment, and iterate fast.
- High bar for quality; you ship fast with high agency and actively jump in to fix problems (not settling for 90%).
- Prior experience founding a company or building products at early stages.
- Experience with prompt engineering, fine-tuning, or building AI agents.
- Keeps up with the latest developments in ML/AI.
Responsibilities
- Integrating and optimizing LLM calls for structured extraction, form filling, and complex document understanding tasks.
- Building and improving document processing pipelines that handle everything from PDFs to spreadsheets at scale, based on vision models and LLMs.
- Making improvements to API design and pre-processing algorithms (chunking, structured extraction, etc.) based on critical customer feedback.
- Experimenting with new techniques and output structures to improve LLM accuracy and reduce latency.
- Building internal tooling and evals to better understand and analyze failure cases.
- Working directly with the founders and customers to shape the product direction and engineering strategy.
Other
- 100% On-site in San Francisco, CA.
- The role requires working hard and moving quickly.
- Unlimited PTO.
- Visa sponsorship is not available.
- High agency, full-development-lifecycle role.
