CUDA Engineer

19 hours, 42 minutes ago
Full-time
Senior
Software Development
Fuse Energy

Fuse Energy

Fuse Energy is a leading UK electricity supplier prioritizing affordability, service excellence, and sustainability through renewable energy projects and global reinvestment efforts.

Renewable Electricity
11-50
Founded 2014
$78M raised

Description

  • Write and optimize custom CUDA kernels for core transformer inference operations.
  • Profile kernels to identify and eliminate bottlenecks in occupancy, memory throughput, and warp divergence.
  • Apply kernel fusion to reduce memory round-trips and launch overhead across inference pipelines.
  • Optimize memory access patterns and manage the memory hierarchy for maximum bandwidth utilization.
  • Implement quantisation-aware kernels and mixed-precision arithmetic to reduce latency and memory footprint.
  • Build and tune caching mechanisms for efficient autoregressive decoding.
  • Tune kernel launch configurations for target GPU architectures.
  • Benchmark kernels against existing baselines and drive measurable throughput and latency improvements.
  • Write tests for CUDA code to catch performance and correctness regressions.
  • Maintain internal CUDA libraries and contribute to coding standards and documentation.

Requirements

  • 4+ years writing production CUDA code, with a track record of shipping performance-critical kernels.
  • Deep understanding of GPU microarchitecture, warps, occupancy, register pressure, and memory hierarchy.
  • Strong CUDA C++ skills, including streams and asynchronous execution.
  • Hands-on experience profiling to diagnose compute-bound vs. memory-bound bottlenecks.
  • Experience with kernel fusion, memory coalescing, and avoiding warp divergence.
  • Experience writing quantised and mixed-precision kernels.
  • Solid grasp of parallel algorithm design and numerical precision tradeoffs.
  • Experience with transformer/attention-style kernels or autoregressive decoding (nice to have).
  • Experience building high-performance GPU libraries from scratch (nice to have).
  • Background in HPC or other latency-critical performance engineering (nice to have).
  • Exposure to multi-GPU or multi-node kernel-level optimisation (nice to have).
  • Comfortable reading PTX/SASS to validate kernel efficiency (nice to have).

Benefits

  • Competitive salary and an equity sign-on bonus.
  • Biannual bonus scheme.
  • Fully expensed tech to match your needs.
  • Breakfast and dinner allowance for office-based employees.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

VP of Solutions Architect - AI

Robots & Pencils 51-250 IT Services

Robots & Pencils is hiring an AWS AI Solutions Architect to design and deliver enterprise-grade generative and agentic AI platforms on AWS for strategic clients.

API Gateway AWS AWS CDK CI/CD CloudFormation Deep Learning DynamoDB HIPAA MLOps OpenSearch Python React SageMaker Serverless Terraform
18 hours, 12 minutes ago

AI Engineer (gn)

The Quality Group Health Care Providers & Services

The Quality Group is hiring a mid-to-senior AI Engineer in Germany to turn business needs into production-ready AI solutions across enterprise tools, automations, and a company-wide AI platform.

LLM Machine Learning Python
18 hours, 13 minutes ago

Senior Machine Learning Engineer

Tripledot Studios is hiring an AI/ML engineer to work within its central AI group on personalization and experimentation for mobile games across studios and central teams.

Apache Airflow CI/CD Docker Generative AI Git Kubeflow Kubernetes Machine Learning Matplotlib MLflow MLOps Python Reinforcement Learning SQL Trino
18 hours, 27 minutes ago

AI Engineer (gn)

The Quality Group Health Care Providers & Services

The Quality Group seeks a Mid-Senior AI Engineer in Germany to turn business needs into productive AI solutions and help build out its enterprise AI platform.

Agile Generative AI LLM Machine Learning Python
18 hours, 27 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers