Hybrid GPU Engineer — Real-time Rendering & ML

Luxoft; Schweiz; Hybrid; CHF 120.000 - 180.000; Vollzeit

Zusammenfassung

Luxoft is seeking hybrid engineers to join a GPU software team working at the intersection of rendering and image ML for real-time visual applications. The role combines graphics rendering pipelines with ML model integration and GPU performance optimization; collaboration with graphics and driver teams is essential.

Candidates should have deep experience in C++, GPU programming with DX12/Vulkan, and ML on images using PyTorch, ONNX Runtime or TensorRT.

Qualifikationen

• 4+ years of professional software engineering experience required.
• Strong C++ background with Python for ML components.
• Hands-on GPU/graphics programming with DX12 and/or Vulkan or CUDA/HIP.

Aufgaben

• Develop and optimize rendering and ML inference components for real-time visual pipelines (DX12, Vulkan, ONNX-based stacks).
• Profile GPU workloads and tune for latency, memory and throughput.
• Integrate ML models (super-resolution, denoising) into graphics pipelines.
• Evaluate output quality using PSNR/SSIM, LPIPS and visual regression tooling.
• Write clean, testable, reproducible code and collaborate with graphics, ML and platform teams.

Kenntnisse

C++ programming

Python for ML

GPU fundamentals

DX12/Vulkan

Shader/Kernel authoring

GPU profiling

PyTorch / ML on images

ONNX Runtime / TensorRT

Quantization

Tools

RenderDoc

Nsight

PIX

Radeon GPU Profiler

CUDA

HIP

ONNX Runtime

TensorRT

Jobbeschreibung

Luxoft is seeking hybrid engineers to join a GPU software team working at the intersection of rendering and image ML for real-time visual applications. The role combines graphics rendering pipelines with ML model integration and GPU performance optimization; collaboration with graphics and driver teams is essential.

Candidates should have deep experience in C++, GPU programming with DX12/Vulkan, and ML on images using PyTorch, ONNX Runtime or TensorRT.