GPU Software Engineer (Graphics / ML)

Luxoft Poland; Town of Poland (NY); On-site; USD 120,000 - 190,000; Full time

Job summary

Luxoft Poland is seeking engineers to join a GPU software team working at the intersection of real-time graphics and machine learning (upscaling, denoising, artifact suppression for interactive visual applications). The role covers rendering pipelines, ML model integration and GPU performance optimization in collaboration with graphics and driver teams.

You will develop and optimize rendering and ML inference components for real-time visual pipelines (DX12, Vulkan, ONNX-based stacks) and profile

Qualifications

• 4+ years of software engineering experience with C++ (for ML-focused candidates: strong Python with working-level C++).
• Solid GPU fundamentals: pipeline, synchronization and memory models, performance trade-offs.
• Deep expertise in at least one area: real-time graphics (DX12/Vulkan, shader authoring, GPU debugging/profiling) OR image ML (PyTorch, super-resolution/denoising/optimization).
• Working awareness of the other area: model integration into rendering pipelines.
• Hands-on performance profiling and optimization of real workloads.
• Ray tracing, game engines, or rendering middleware are a plus.
• CI-driven development and automated test harnesses are a plus.

Responsibilities

• 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 objective and perceptual metrics (PSNR/SSIM, LPIPS) and visual regression tooling.
• Author clean, testable, reproducible code; collaborate with graphics, ML and platform teams.

Skills

C++

Python

GPU fundamentals

DX12

Vulkan

Shader authoring

HLSL

GLSL

RenderDoc

PIX

Radeon Profiler

PyTorch

ONNX Runtime

TensorRT

Quantization

Model integration

Profiling

Job description

We are looking for engineers to join a GPU software team working at the intersection of real-time graphics and machine learning (upscaling, denoising, artifact suppression for interactive visual applications). The work spans rendering pipelines, ML model integration and GPU performance optimization, in collaboration with graphics and driver teams.

Responsibilities

• Develop and optimize rendering and/or 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 objective and perceptual metrics (PSNR/SSIM, LPIPS) and visual regression tooling.
• Author clean, testable, reproducible code; collaborate with graphics, ML and platform teams.

Skills

Must have

• 4+ years of software engineering experience with C++ (for ML-focused candidates: strong Python with working-level C++).
• Solid GPU fundamentals: pipeline, synchronization and memory models, performance trade-offs.
• Deep expertise in at least one of the two areas:
• (a) real-time graphics: DX12 and/or Vulkan, shader authoring (HLSL/GLSL), rendering techniques, GPU debugging/profiling (RenderDoc, PIX, Radeon GPU Profiler), OR
• (b) image ML: PyTorch, super-resolution/denoising/artifact-suppression models, inference deployment and optimization on GPU (ONNX Runtime or TensorRT, quantization).
• Working awareness of the other area: ability to integrate a pre-trained model into a rendering pipeline, or understanding of how ML components fit into graphics stacks.
• Hands-on performance profiling and optimization of real workloads.

Nice to have

• Ray tracing (DXR/VKRT), game engines (Unreal, Unity) or rendering middleware.
• Color and image processing fundamentals (sRGB vs linear, HDR, resampling/filtering).
• Render fidelity testing, SSIM/PSNR-based visual regression tooling.
• CI-driven development, automated test harnesses.