Get the latest tech news

OmniAI (YC W24) Hiring Engineers to Build Open Source Document Extraction

Engineering at Omni! Help us build the best OCR / document extraction on the planet! We’re looking for founding engineers to join our team. If you’ve ever dreamed of exploring the fascinating and terrible world of PDFs, this is your chance! You can check out our open source library: https://github.com/getomni-ai/zerox And try out our OCR model: https://getomni.ai/ocr-demo What will we be working on The main things we spend our time on: Wrangling LLMs into providing predictable outputs Running document extractions at scale Building training data for vision models (https://getomni.ai/blog/infinite-pdf-generator) All of these problems are hard, especially in conjunction with each other. If you’ve had any experience with structured LLM output, we’d love to chat. Tech Stack The primary tech stack is Node, TypeScript, React/NextJS, Postgres, Docker. For our integrations we support MySQL, Snowflake, Mongo, BigQuery and more. We don’t use these much internally, but our customers do so it’s helpful to know. On the LLM side, we interface with OpenAI, Mistral, Llama, and Anthropic, so users have the choice of model to run. Companies can use Omni via the cloud product, or a VPC deploy. So knowledge of Docker + devops is a big plus.

Wrangling LLMs into providing predictable outputs Running document extractions at scale Building training data for vision models ( https://getomni.ai/blog/infinite-pdf-generator) On the LLM side, we interface with OpenAI, Mistral, Llama, and Anthropic, so users have the choice of model to run. Only 20% of corporate data fits in a SQL table today, with the rest scattered across unstructured formats (customer reviews, chat logs, transcripts, PDFs, etc.)

Get the Android app