> Markdown version of [/jobs/ext/4027310-backend-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4027310-backend-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Backend/AI Engineer

- **Company:** Reducto, Inc.
- **Location:** San Francisco, CA, United States
- **Experience:** Experienced
- **Contract:** Permanent contract
- **Skills:** Testing (Software), Artificial Intelligence, Computer Vision, Spreadsheets, Data Files, Software Debugging, Document Type Definition, Statistical Hypothesis Testing, Information Extraction, Python (Programming Language), Systems Development Life Cycle, SimpleText, Systems Integration, Workflow Management Systems, Document Metadata, Large Language Models, Prompt Engineering, Backend, Agentic-AI, Api Design, Streamlit Framework
- **Published:** October 30, 2026
- **Apply:** https://www.careerbuilder.com/job-details/backend-ai-engineer-san-francisco-ca--c4f3a033-09c2-4edb-9943-f52527edce42

## About the Role

Artificial Intelligence (AI), Documentation, Artificial Intelligence (AI), Team Lead/Manager, Revenue Growth, Benchmarking, Production Systems, Data Sets, Software Testing, Test Plan/Schedule, * Philosophy: 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.

 * Experience: You have 2+ years of experience building real world applications and integrating LLMs into production systems
 * Language: You're exceptional at Python
 * Tools: Build your own tools as needed-like a quick Streamlit app to test hypotheses or create a dataset.
 * Approach: A quantitative approach to building products. Ability to debug, experiment, and iterate fast. You should be comfortable getting hands-on with the full development lifecycle, from ideation to shipping to users., * Have prior experience founding a company or building products at early stages
 * Have experience with prompt engineering, fine-tuning, or building AI agents
 * Are ambitious and driven, and care a lot about doing great work with great people
 * Keep up with the latest developments in ML/AI

## Description

* Integrating and optimizing LLM calls for structured extraction, form filling, and document understanding tasks
 * 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
 * Experimenting with new techniques and output structures to improve LLM accuracy and reduce latency
 * 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, PDFs are the status quo for enterprise knowledge in nearly every industry. Insurance claims, financial statements, invoices, and health records are all stored in a structure that's simply impractical for use in digital workflows. This isn't an inconvenience-it's a critical bottleneck that leads to dozens of wasted hours every week.

Traditional approaches fail at reliably extracting information in complex PDFs

OCR and even more sophisticated ML approaches work for simple text documents but are unreliable for anything more complex. Text from different columns are jumbled together, figures are ignored, and tables are a nightmare to get right. Overcoming this usually requires a large engineering effort dedicated to building specialized pipelines for every document type you work with.

Reducto breaks document layouts into subsections and then contextually parses each depending on the type of content. This is made possible by a combination of vision models, LLMs, and a suite of heuristics we built over time. Put simply, we can help you:

 * Accurately extract text and tables even with nonstandard layouts
 * Automatically convert graphs to tabular data and summarize images in documents
 * Extract important fields from complex forms with simple, natural language instructions
 * Build powerful retrieval pipelines using Reducto's document metadata
 * Intelligently chunk information using the document's layout data