Build the future of vector search

Vector Panda is a distributed vector database built from scratch in Rust — currently by one person. Anyone who joins has direct impact on architecture, performance, and product direction from day one, because there's no layer between you and the system.

How we work

Ship fast, measure everything

Deploys go to production several times a day. Every change is measured against real query latency, throughput, and recall benchmarks. If it doesn't move a metric, it gets questioned.

Depth over breadth

One person who deeply understands SIMD-optimized distance calculations beats three who can set up a Kubernetes cluster. Expertise in systems programming, linear algebra, and distributed systems is what counts here.

No complexity budget overruns

Every abstraction has a cost. Three clear lines of code beat a premature abstraction, and the codebase stays small enough to hold the whole system in your head.

Our stack

Coordinator
Rust + Tokio
Workers
Rust + SIMD
Transport
WebSocket + bincode
Storage
Memory-mapped files
Client API
HTTP + JSON
Metadata
SQLite
Consumer Site
Node.js + EJS
Infrastructure
Bare metal Linux

Open positions

We don't have any open positions right now. Vector Panda is one person today, and hiring happens opportunistically when the right person shows up.

Interested anyway?

If you're passionate about systems programming, vector search, or distributed databases and want to work on hard problems close to the metal, the founder would like to hear from you.

Send us a note