Building the next generation multi-silicon AI cloud and runtime platform.
Palo Alto, California
Yotta Labs is at the forefront of building the next generation multi-silicon AI cloud and runtime platform. We enable training and inference across NVIDIA GPUs, AMD GPUs, and AWS Trainium/Inferentia, helping AI companies achieve the best performance and economics across heterogeneous hardware
Remote · Copenhagen, Capital Region of Denmark, Denmark
Implement and optimize compute kernels for AI workloads on NVIDIA, AMD, and AWS Trainium hardware. Profile and improve inference performance in runtimes like vLLM and SGLang while contributing to open-source AI infrastructure.
Remote · Canada
Design and implement high-performance kernels for various AI tasks and optimize them for different hardware. Contribute to open-source projects and engage with the developer community.
