Compiler Engineer - AI Inference

Salary: £63,000 - 103,000 per year

Requirements:

• BS or MS in Computer Science, Computer Engineering, or a related field, or equivalent experience
• A PhD is strongly preferred
• 3+ years of relevant industry experience specializing in compiler optimizations, synthesis, and placement
• Demonstrated, hands-on experience working with MLIR
• Exceptional C/C++ and Python programming and software design skills, including rigorous debugging, performance analysis, and test design
• Strong communication and interpersonal skills, with the ability to collaborate effectively in a dynamic, fast-paced, and product-oriented environment
• Hands-on experience implementing complex AI workloads on CPU, GPU, and/or custom AI accelerator architectures
• Deep understanding of Large Language Model (LLM) inference and its implications on computer architecture
• Demonstrated understanding in designing and architecting comprehensive compiler frameworks from the ground up

Responsibilities:

• Drive technical innovation through hands-on development focused on kernel generation and computational graph optimizations for next-generation NVIDIA GPUs
• Solve complex compilation problems for AI workloads, including inference and training, and transition these breakthroughs into enterprise and consumer products
• Partner with experts across software, hardware, and research divisions to architect and co-design future silicon
• Participate in the advancement and optimization of datacenter-scale AI workload deployments

Technologies:

• AI
• Architect
• Hardware
• LLM
• Python

More:

We are NVIDIA, the AI computing company, building technology that powers the next generation of computing. We offer competitive salaries and a generous benefits package, and we are widely considered one of the technology worlds most desirable employers. Our engineering teams are rapidly growing due to unprecedented growth, and we are looking for creative, autonomous engineers with a passion for technology. This is a full-time role based in the UK, with remote options and Cambridge listed as a location.

last updated 35 week of 2026