Mid or Senior AI Infrastructure Engineer

Description

The software team at semydynamics is developing the tools and frameworks that enable clients to deploy AI applications on Semidynamics’ hardware. We’re looking for AI engineers with experience in AI model deployment in HPC/Cloud provider environments. If you have a passion for AI and want to help bring the future of AI acceleration to market, you’ll find the right challenges with us.

Requirements

Required:

• AI Model deployment frameworks (e.g. vLLM/SGLang/Triton/DeepSpeed)
• Model serving in HPC/Cloud environments
• Multi-node and Multi-GPU deployment and optimization
• ScaleUp and ScaleOut Solution
• Strong problem-solving skills and attention to detail
• English level C1
• 4+ years of experience in the role
• Bachelor, Master or PhD

Desired:

• vLLM/SGLang/Triton/DeepSpeed
• Tensor-RT
• ONNX-RT
• CUDA/ROCm,
• Tensorflow
• C++ experience
• C/C++ and python interoperability experience
• Master or PhD
• Assembly
• Baremetal programming
• Software profiling and architecture-based optimization