At Exa, we train, embed, and serve our own large-scale search index and models for perfect retrieval over the internet.
See open rolesSEPTEMBER 2025
The world is ready for a new type of search
JULY 2025
AI systems need faster search than humans. They now have it.
JUNE 2025
Agentic search that doesn’t stop until it finds what you need
MAY 2025
We're state of the art at search for LLMs. But how do we measure that?
Our 18-node GPU cluster training our next-gen search models
How we cut our BM25 index footprint in half at billions-document scale without sacrificing performance.
DECEMBER 2024
It uses clustering, matryoshka embeddings, binary quantization, and SIMD operations. Written in rust of course 🦀
FEBRUARY 2024
Serving real-time embeddings at scale is challenging. To launch Exa Highlights, we 4X’ed throughput by migrating from Python to Rust.
AUGUST 2023
Our information ecosystem is broken, and the best way to fix it is to combine LLMs with high quality content from the Internet
Our technical team is small and growing quickly. If you are an exceptional AI researcher or engineer, join us to make an outsized impact.
See open roles