Reducto helps AI teams ingest real world enterprise data with state of the art accuracy. The vast majority of enterprise data — from financial statements to health records — is locked in unstructured file formats like PDFs and spreadsheets. We train vision models to read those documents the way a human would, and make it possible to build products, train models, and automate processes at scale.
Requirements
- 5+ years of experience building, hardening and scaling real world applications
- 2+ years of experience integrating LLMs into production systems
- Exceptional with Python or have a deep understanding of another language of choice
- Build your own tools as needed—like a quick Streamlit app to test hypotheses or create a dataset
- Ability to debug, experiment, and iterate fast
- Comfortable getting hands-on with the full development lifecycle, from ideation to shipping to users
- Experience with prompt engineering, fine-tuning, or building AI agents
Responsibilities
- Integrating and optimizing LLM calls for structured extraction, form filling, and document understanding tasks
- Experimenting with new techniques and output structures to improve LLM accuracy and reduce latency
- Making improvements to API design and pre-processing algorithms (chunking, structured extraction, etc.) based on customer feedback
- Building and improving document processing pipelines that handle everything from PDFs to spreadsheets at scale
- Driving backend latency and costs down without sacrificing quality
- Building internal tooling and evals to better understand/analyze failure cases
- Working directly with the founders and customers to shape the product direction and engineering strategy
Other
- You are your own worst critic. You have a high bar for quality and don't rest until the job is done right—no settling for 90%.
- We want someone who ships fast, with high agency, and who doesn't just voice problems but actively jumps in to fix them.
- We prefer generalists who are immensely curious to dive deep.
- A quantitative approach to building products.
- This is an in person role at our office in SF. We're an early stage company which means that the role requires working hard and moving quickly. Please only apply if that excites you.
