AI Kernel Engineer

AI Kernel Engineer Overview

This opportunity is with a well-funded AI systems company that focuses on improving the performance and efficiency of next-generation AI hardware. The business works with major semiconductor vendors, server makers and cloud platforms to push modern AI systems to perform better. The role is suited to engineers who enjoy deep technical problem-solving, especially where software and hardware meet, and who want to work on accelerator architectures before they reach mass production.

The position is centred on performance optimisation across the AI stack. You would be analysing machine learning workloads, identifying where bottlenecks occur, and implementing low-level improvements that make a measurable difference to throughput, latency and efficiency. The work is highly technical and collaborative, with close interaction across engineering teams and customer-facing stakeholders.

What you would do

• Improve the performance of compute-intensive AI workloads running on GPUs, AI accelerators and other emerging hardware.
• Build, tune and refine low-level kernels used in machine learning applications.
• Measure and study system behaviour using standard profiling, benchmarking and analysis tools.
• Track down performance constraints that appear across both software and hardware layers.
• Partner with customers and internal engineers to deliver practical performance gains.
• Contribute to benchmarking work and broader evaluation of AI system performance.
• Investigate new approaches to accelerator programming and methods that use AI to assist optimisation.
• Examine AI models and workload patterns to understand where improvements can be made.

What the company is looking for

• A degree in Computer Science, Computer Engineering, Mathematics, Physics or a similar technical field.
• Experience improving workloads on GPUs, AI accelerators, FPGAs or comparable high-performance hardware.
• A solid grasp of performance analysis, profiling and benchmarking techniques.
• Practical use of profiling, debugging and performance-analysis tools.
• Background in inference optimisation or other AI systems where performance is critical.
• Strong coding skills in C++ and/or Python.
• Good communication skills and the ability to work well in a team that values research and technical collaboration.

What is on offer

• A salary of £90,000.
• A remote role based in the UK.
• The chance to work for a well-funded company operating at the leading edge of AI hardware performance.
• Exposure to advanced accelerator architectures and complex optimisation challenges.
• Collaboration with a highly technical team and with external partners across the semiconductor and cloud ecosystem.
• Work that has direct impact on real performance outcomes such as throughput, latency and efficiency.

How to apply

For further information, contact Harry Hansford at IC Resources. The posting also provides an Apply Now option for candidates who want to submit an application directly.

Degree Requirement: Bachelor’s

Visa Sponsorship May be