CUDA Developer | High-Performance Computing | Applied AI
Location: UK-based Remote
Type: Contract, Outside IR35, Remote
Sector: Advanced Computing / Applied AI
We’re partnering with a company building next-generation GPU-accelerated software for scientific and AI applications. We are recruiting for a CUDA Developer who’s passionate about getting every ounce of performance out of modern hardware — someone who loves tuning kernels, benchmarking workloads, and finding elegant solutions to complex computational problems.
This is an opportunity to work with a small, expert team where your technical decisions will shape the foundation of an emerging AI technology.
What You’ll Be Doing
* Designing and optimising CUDA kernels for high-performance workloads.
* Translating advanced algorithms into production-ready GPU-accelerated code.
* Profiling performance and reducing bottlenecks using Nsight, CUPTI, and custom tooling.
* Working with C++ engineers and ML researchers to deliver scalable AI computation pipelines.
* Contributing to architecture decisions on parallelisation, data transfer, and memory efficiency.
What We’re Looking For
* Deep experience with CUDA C/C++ and modern C++ (17/20).
* Strong understanding of GPU architecture, memory management, and parallelism.
* Familiarity with OpenMP, MPI, or other HPC frameworks.
* Bonus points for exposure to AI/ML workloads or scientific computing.
* Pragmatic and collaborative — you enjoy working in fast-moving, high-impact environments.
Why This Role?
You’ll be part of a technically elite, low-ego team solving problems at the cutting edge of performance engineering. Your work will be deeply visible. The difference between “it works” and “it flies”. If you love performance, parallelism, and precision, then please apply with a current CV for more information.