Build the infrastructure that runs AI
We're hiring engineers who believe AI infrastructure should be sovereign, efficient, and built to outlast any single provider's roadmap.
$8M to Revolutionize AI Inference at the Edge
Read the coverage →
AI Model Architecture Optimization Engineer R&D
Research and develop acceleration techniques for transformer architectures, integrated into the PyTorch stack.
San Mateo, CA · Full-time →
Full-Time Engineer: AI Software Engineer
Build and maintain the Rust-based LLM inference engine, deployed across Windows, Linux, macOS, Android, and iOS.
Bay Area, CA · Full-time →
Senior On-Device AI Inference Performance Engineer
Build and optimize the inference engine for on-device AI — C/C++, low-level systems, power and performance.
San Mateo, CA · Full-time →
Don't see your role? Reach out at [email protected]