GPU kernel engineer · United Kingdom · remote

I build and optimize CUDA kernels and GPU pipelines for AI and HPC workloads.

I work below the framework line: kernels written by hand, SASS read in Nsight Compute, memory traffic priced in bytes per element before the first line is written. Ten years of low-level C++ on compute and memory bound workloads across AI compute, real-time video, simulation and numerical methods.

Open to remote GPU kernel and performance work, contract or full-time.

Experience

Mar 2026 – Sep 2026

Senior HPC Engineer · Jugo

Contract · Remote · United Kingdom

Custom CUDA kernels for live AI video on Jugo's immersive meetings platform, which renders real-time 3D environments in Unreal Engine on cloud GPUs. Built the GPU compositing stage that injects game-engine frames into NVIDIA DeepStream, and cut P95 per-frame latency from 25.1 ms to 18.3 ms on RTX PRO 6000 Blackwell through Nsight-driven profiling.

HIP/ROCm · System Performance · C++ · CUDA · High Performance Computing · GPGPU · Performance Tuning

Jun 2024 – Apr 2026

Co-founder & Technical Lead · NitroSpark AI

Full-time · Hybrid · United Kingdom

Co-founded NitroSpark AI and served as Technical Lead.

Aug 2018 – Aug 2024

GPU Systems Engineer · Union One

Contract · Remote · United Kingdom

Delivered the GPU-resident render pipeline for Union One, a tactical FPS: particle systems and related effects computed on the GPU rather than the CPU, with Vulkan driving rendering and the surrounding engine systems. Managed systems under frame budget and memory layout constraints, profiled and optimized to target per-frame time budget.

System Performance · OpenGL Shading Language (GLSL) · C++ · GPGPU · Performance Tuning

Skills

CUDA

C++

High Performance Computing

Nsight Compute

Nsight Systems

PTX / SASS

GLSL / Slang

cuSPARSE

NPP

OpenMP

Minimalist Envelope Scene

Want to get in touch?

Feel free to reach out via email: