AI Runtime Engineer: Build Next-Gen AI Platform

Modular, a Qualcomm company; City of Edinburgh; Presencial; GBP 83 000 - 124 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

World-class benefits

RSU grants

Team building events

Resumo da oferta

Modular, a Qualcomm company, is seeking an AI Runtime Engineer in Edinburgh to own a runtime across CPU, GPU, and accelerator hardware. You will optimize performance for diverse AI models and collaborate with compiler, kernels, and models teams to push end-to-end efficiency.

The role requires 2+ years in HPC, strong C++ skills, and experience profiling CPU/GPU workloads. On-site in Edinburgh with relocation assistance for eligible candidates.

Qualificações

• 2+ years of experience working on high-performance computing systems.
• Proficiency in C++ and complex software systems.
• Experience with CPU/GPU/runtime optimizations and performance analysis.

Responsabilidades

• Design and develop runtime and cross-stack optimizations to improve CPU, GPU, and accelerator efficiency across devices.
• Work with vendor-specific networking libraries to unlock high performance data transfer for multiple topologies.
• Collaborate with compiler, kernels, serving, and models teams to achieve state-of-the-art end-to-end performance on CPU and GPU hardware.
• Collaborate with the customer success team to understand performance requirements and use cases.
• Collaborate with tooling and infrastructure teams to design systems for automated performance analysis and benchmarking.

Conhecimentos

HPC experience

C++ programming

Runtime optimizations

Profiling tools

Team collaboration

Descrição da oferta de emprego

Modular, a Qualcomm company, is seeking an AI Runtime Engineer in Edinburgh to own a runtime across CPU, GPU, and accelerator hardware. You will optimize performance for diverse AI models and collaborate with compiler, kernels, and models teams to push end-to-end efficiency.

The role requires 2+ years in HPC, strong C++ skills, and experience profiling CPU/GPU workloads. On-site in Edinburgh with relocation assistance for eligible candidates.