Full Stack Engineer at OmniAI

Omni Engineering!

Help us build the best OCR / document retrieval on the planet!

We are looking for a founding engineer to join our team. If you’ve been dreaming of exploring the fascinating and terrifying world of PDFs, this is your chance!

You can check out our open source library: https://github.com/getomni-ai/zerox

And try our OCR model: https://getomni.ai/ocr-demo

What are we going to do

The main things we spend our time on:

1. LLMs struggle to provide predictable outputs
2. Run document retrieval at scale
3. Building training data for vision models (https://getomni.ai/blog/infinite-pdf-generator)

All these problems are difficult, especially in relation to each other. If you have experience with structured LLM output, we’d love to chat.

Tech Stack

The main tech stacks are Node, TypeScript, React/NextJS, Postgres, Docker. For our integrations we support MySQL, Snowflake, Mongo, BigQuery and more. We don’t use it 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 a choice of models to run.

Companies can use Omni through a cloud product, or VPC deployment. So knowledge of Docker + devops is a big plus.