Real-Time GPU Rendering & ML Engineer

Luxoft; Poland; On-site; PLN 180,000 - 240,000; Full time

Benefits offered by this job

Private medical & dental care

Life Insurance

Internal mobility program

Rotation between projects/locations

Job summary

Luxoft is seeking a GPU software engineer to join a team working at the intersection of real-time graphics and machine learning. You will develop rendering and ML components, optimize GPU performance, and work across DX12, Vulkan, and ONNX-based stacks with engineers from graphics and driver teams.

You will profile workloads, optimize latency and throughput, and integrate ML models into graphics pipelines, collaborating with cross-functional teams to deliver high-quality visual experiences.

Qualifications

• 4+ years of software engineering experience with C++.
• Strong GPU fundamentals: pipelines, synchronization, memory models.
• Expertise in real-time graphics (DX12 and/or Vulkan) or image ML (PyTorch, ONNX/TensorRT).
• Experience deploying ML models on GPU and optimizing for latency.
• Ability to profile and optimize real workloads.

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++

GPU fundamentals

DX12/Vulkan

ML model integration

Performance profiling

Tools

RenderDoc

PIX

ONNX Runtime

TensorRT

Job description

Luxoft is seeking a GPU software engineer to join a team working at the intersection of real-time graphics and machine learning. You will develop rendering and ML components, optimize GPU performance, and work across DX12, Vulkan, and ONNX-based stacks with engineers from graphics and driver teams.

You will profile workloads, optimize latency and throughput, and integrate ML models into graphics pipelines, collaborating with cross-functional teams to deliver high-quality visual experiences.