Founding GPU Engineer

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Design, develop, and enhance CUDA kernels tailored for high-throughput, latency-sensitive applications.

• Analyze and optimize GPU performance by addressing compute, memory bandwidth, and interconnect (NVLink/PCIe) constraints.

• Create tools that link GPU cluster power consumption and utilization with real-time energy pricing and grid signals.

• Enhance multi-GPU and multi-node scaling using NCCL, MPI, or similar communication frameworks.

• Collaborate with data center infrastructure teams on strategies for power capping, dynamic voltage/frequency scaling, and workload scheduling that minimize energy costs and carbon emissions.

• Work alongside ML/systems engineers to embed custom kernels into training and inference workflows.

• Perform benchmarking against CPU/GPU standards and drive ongoing performance enhancements.

• Contribute to the development of internal libraries, documentation, and best practices for GPU performance engineering.

⛳️ Requirements

• A minimum of 4 years of experience in writing production-level CUDA code, or comparable extensive project/industry experience.

• Profound knowledge of GPU architecture, including SMs, warps, memory hierarchy, and occupancy.

• Expertise in C++ and CUDA; familiarity with Python for tooling and orchestration.

• Experience with performance profiling tools such as Nsight Systems and Nsight Compute.

• Understanding of multi-GPU/multi-node scaling techniques (NCCL, MPI, RDMA/InfiniBand).

• Strong foundation in memory optimization, kernel fusion, and the design of parallel algorithms.

• Ability to work across all layers, from low-level kernels to system-level infrastructure.

• **Nice to Have**

• Experience with Triton, cuDNN, cuBLAS, or custom ML inference/training frameworks.

• Familiarity with data center power and thermal management or demand-response systems.

• Background in HPC, quantitative finance, or large-scale distributed systems.

• Knowledge of Kubernetes or Slurm for GPU cluster orchestration.

• Interest or experience in energy markets, grid systems, or sustainability-oriented computing.

🏝️ Benefits

• Competitive salary along with an equity sign-on bonus.

• Biannual bonus program.

• Fully covered technology expenses to suit your requirements.

• Breakfast and dinner allowances for employees working in the office.