Backend/AI Engineer
AI summary of the role
Backend/AI Engineer at a fast-growing document intelligence API startup.
What you’ll do
- Integrate and optimize LLM calls for structured extraction, form filling, and document understanding tasks
- Make improvements to API design and pre-processing algorithms based on customer feedback
- Build and improve document processing pipelines handling PDFs to spreadsheets at scale
- Experiment with new techniques to improve LLM accuracy and reduce latency
What you’ll bring
- 2+ years of experience building real world applications and integrating LLMs into production systems
- Exceptional at Python
- Comfortable building your own tools (e.g., Streamlit apps) to test hypotheses
- Quantitative approach to building products with ability to debug, experiment, and iterate fast
Technologies
LLMs · Python · Streamlit · API design · document processing · structured extraction · prompt engineering · fine-tuning · AI agents
About Reducto
Reducto uses OCR plus vision-language models to convert complex unstructured documents into clean, LLM-ready inputs, sold as an enterprise API.
Series B · 50–200 people
Source and classification
Production engineering · Evidence for this classification:
About Reducto Reducto is the agentic document platform for leading AI teams who demand enterprise performance at scale. We provide a comprehensive toolkit for working with documents the way a human would, combining custom in-house and leading frontier models to power efficient and accurate document workflows. We’ve grown rapidly, increasing revenue 8x year over year and partnering with hundreds of companies, from leading AI teams like Harvey, Vanta, and Scale, to enterprise customers across FAANG and top trading firms. Reducto has raised over $100M from world-class investors including a16z, Benchmark, and First Round Capital. The Opportunity As a Backend/AI Engineer, you'll work on our core API that powers document parsing for hundreds of companies. You'll integrate cutting-edge LLMs, optimize document processing pipelines, and build the infrastructure that makes state-of-the-artHow jobs are selected
Employer postings · Data from · Sources