GPU Software Engineer (Graphics / ML)

Luxoft; Town of Poland (NY); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Private medical insurance

Dental insurance

Life insurance

Internal mobility

Job summary

Luxoft is seeking experienced GPU software engineers to join a real-time graphics and ML focused team in upstate New York. You will develop rendering or ML inference components, optimize GPU pipelines, and collaborate across graphics, ML and platform teams.

The role demands strong C++ background (and Python for ML tasks), solid GPU fundamentals, and hands-on experience with DX12/Vulkan or ML frameworks. Options include model integration and performance profiling.

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 real-time graphics: DX12 and/or Vulkan, shader authoring (HLSL/GLSL).
• Or image ML: PyTorch, super-resolution/denoising models, deployment on GPU (ONNX Runtime or TensorRT, quantization).
• Working awareness of the other area: integrating a pre-trained model into a rendering pipeline.

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

C++

Python

GPU basics

Real-time graphics

ML integration

Tools

RenderDoc

PIX

ONNX Runtime

TensorRT

Job description

• Private Medical & Dental care & Life Insurance covered
• Internal Mobility program - possibility of rotation between projects, locations, accounts
• ...and more!

Project 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.

Mandatory Skills Description

• 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 Skills Description

• 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.