Senior Embedded Vision Architect for Real-Time AI

Luxoft; United Kingdom; Remote; GBP 90,000 - 130,000; Full time

Job summary

Luxoft in the United Kingdom is seeking a hands-on technical leader to design and optimize high-performance computer vision and AI pipelines for consumer devices on embedded platforms.

You will mentor engineers, drive performance optimizations in C++14/17/20, integrate ML models with TFLite, TensorRT, ONNX, and collaborate with Android/Linux teams to ensure real-time latency, power efficiency, and robust validation across SoCs.

Qualifications

• Bachelor's or Master's in Computer Science, Electrical Engineering, or related field.
• 7–10+ years of experience in computer vision and image processing.
• Proven track record shipping embedded vision/AI products.
• Strong C++ (C++14/17/20) optimization.
• Experience with OpenCV and ML frameworks (PyTorch, TensorFlow, ONNX).
• Experience deploying ML models on embedded/edge devices.
• Knowledge of model optimization (quantization, pruning).
• Strong understanding of 2D/3D geometry and linear algebra.
• Experience with embedded Linux or Android.
• Strong debugging and performance profiling skills.
• Experience optimizing for power and thermal constraints.

Responsibilities

• Design and implement advanced computer vision and image processing pipelines optimized for real-time consumer devices.
• Collaborate with ISP, sensor, and tuning teams to optimize image quality for downstream AI and UX performance.
• Develop and deploy ML models for visual recognition, enhancement, tracking, or scene understanding.
• Optimize ML models for edge deployment (quantization, pruning, distillation, hardware-aware tuning).
• Implement performance-critical algorithms in modern C++ for embedded platforms.
• Optimize for latency, power consumption, memory footprint, and thermal constraints.
• Integrate inference engines (TFLite, TensorRT, ONNX Runtime, etc.) on target SoCs.
• Work closely with Android/Linux platform teams to integrate camera and AI pipelines.
• Define and track KPIs: FPS, power usage, memory, startup time, and accuracy.
• Profile and optimize performance across CPU/GPU/NPU/DSP.
• Drive debugging of complex system-level issues in production builds.
• Ensure robust unit testing and contribute to automated validation pipelines.
• Mentor engineers and review architecture/design proposals.
• Support product bring-up and mass production readiness.

Skills

C++ optimization

OpenCV

PyTorch

TensorFlow

ONNX

Embedded Linux

Android

Performance profiling

Edge deployment

Geometry basics

Debugging

Power optimization

Education

Bachelor's or Master's in CS/EE

Tools

CUDA

OpenCL

Vulkan

OpenGL ES

TensorRT

TFLite

ONNX Runtime

Job description

Luxoft in the United Kingdom is seeking a hands-on technical leader to design and optimize high-performance computer vision and AI pipelines for consumer devices on embedded platforms.

You will mentor engineers, drive performance optimizations in C++14/17/20, integrate ML models with TFLite, TensorRT, ONNX, and collaborate with Android/Linux teams to ensure real-time latency, power efficiency, and robust validation across SoCs.