LLM Agents / data engineer (intern)

We have over 20M documents from court cases in our DB already.
You can join us in person in New York City or remote.
We are a small team (5 people) with ex devs from Amazon, Google, You.com, Stanford, TUM, ETH.

Right now Enes is building out our ingestion pipeline, which which we are using agentic scrapers to scale this up to 40M.

We have several importnat projects and will discuss which would be the best fit, they would be in this area

• Work on agentic data extraction pipelines
• Improve our search pipeline.

Our backend stack: Vercel (nextJs), GCP, PostgreSQL, Prisma, Render.com, Pinecone, Cohere, ElasticSearch, Sentry.

Apply if you have experience in writing production applications with SQL / python. Bonus but not required: Nextjs Fullstack experience

Minimum internship duration is 3 months, we recommend 6. We are also hiring full time employees, it is possible to transition to a full time role after this internship.