Back to Careers
Software Engineer - Heterogeneous Runtime
San Francisco, CA (In-Person)
General Diffusion is a foundational AI research lab establishing the scientific discipline of Compute Intelligence. We build frontier models that learn the physics of heterogeneous hardware, decoupling intelligence from infrastructure.
<br/>About the role
As a Software Engineer on the Runtime team, you will build the "glue" that holds our distributed OS together. You will develop the lightweight runtime that sits on every node, managing device memory, kernel launches, and peer-to-peer communication.
<br/>What you might work on
- Optimizing the low-level runtime for minimal overhead (<5us kernel launch latency).
- Implementing zero-copy memory transfer protocols between CPU and accelerators.
- Building robust error handling and recovery mechanisms for hardware failures.
- Developing cross-platform synchronization primitives.
What we’re looking for
- Strong systems programming skills in C++ or Rust.
- Experience with CUDA driver API, ROCm, or OpenCL.
- Understanding of OS concepts (virtual memory, threading, interrupts).
- Passion for squeezing every last drop of performance out of hardware.
Our culture
- Compute Intelligence. We are establishing a new scientific discipline.
- Silicon Neutrality. We build foundational models that run on any chip.
- Deep Work. We value long periods of uninterrupted focus.