AI Runtime Engineer - High-Performance ML Platform

Modular; City of Edinburgh; On-site; GBP 83,000 - 124,000; Full time

Benefits offered by this job

Amazing Team.

World-class Benefits.

Competitive Compensation.

Team Building Events.

Job summary

Modular in Edinburgh is seeking an AI Runtime Engineer to own a runtime across CPU, GPU and accelerator hardware, delivering cross-stack optimizations for diverse models. You will design and implement runtime improvements, optimize performance, and collaborate with multiple teams to reach state-of-the-art end-to-end performance.

The role requires 2+ years in high-performance computing and strong C++ skills, plus experience with performance analysis and profiling tools.

Qualifications

• 2+ years of experience working on high-performance computing systems.
• Experience in C++ programming and complex software systems.
• Experience with CPU or GPU runtime optimizations and performance analysis on CPUs, GPUs, or AI accelerators.
• Proficiency with profiling tools (CPU or GPU).
• Creativity and curiosity for solving complex problems, a team-oriented attitude that enables you to work well with others, and alignment with our culture.

Responsibilities

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

Skills

C++

High-performance computing

Performance analysis

Profiling tools

Team collaboration

Job description

Modular in Edinburgh is seeking an AI Runtime Engineer to own a runtime across CPU, GPU and accelerator hardware, delivering cross-stack optimizations for diverse models. You will design and implement runtime improvements, optimize performance, and collaborate with multiple teams to reach state-of-the-art end-to-end performance.

The role requires 2+ years in high-performance computing and strong C++ skills, plus experience with performance analysis and profiling tools.