As a consultant, you will be embedded in a high‑tech innovation environment, contributing to GPU-accelerated software for healthcare systems and advanced digital processing applications. You will design, develop, and improve C++ and CUDA solutions for computationally intensive workloads such as image reconstruction, signal processing, 3D rendering, simulation, and AI inference. Your work will cover the full software lifecycle, from early prototypes to production-ready components for high-throughput, low-latency systems. Responsibilities
- Design and deliver high-performance C++ and CUDA software for GPU-based digital processing applications.
- Translate signal-processing, image-processing, modelling, and AI algorithms into efficient GPU implementations.
- Profile GPU workloads and identify bottlenecks related to memory access, bandwidth, occupancy, synchronization, and CPU-GPU data transfers.
- Improve algorithms and CUDA kernels through parallelisation, vectorisation, computation reuse, reduced data movement, and kernel fusion.
- Tune complete processing pipelines to meet latency, throughput, resource, and numerical accuracy requirements.
- Define hardware-software partitions with FPGA, electronics, firmware, systems, algorithm, and AI engineers.
- Contribute to architecture decisions, technical reviews, verification activities, and the delivery of production-ready software.
- Document designs, performance results, technical decisions, and integration constraints throughout the product lifecycle.
- Master’s degree or PhD in Computer Science, Electrical Engineering, Computer Engineering, Mathematics, Physics, Biomedical Engineering, or a related field.
- 5+ years of experience developing high-performance software for embedded, scientific, industrial, or healthcare applications.
- Strong command of modern C++ and object-oriented design principles, including design patterns, maintainability, testing, and code quality.
- Deep experience with GPU programming in CUDA, including kernel design, memory hierarchy, bandwidth, occupancy, synchronisation, and asynchronous execution.
- Hands-on experience with GPU performance analysis using tools such as NVIDIA Nsight Systems, NVIDIA Nsight Compute, or equivalent profilers.
- Solid knowledge of signal processing, image processing, numerical methods, computational modelling, physics-based simulation, or scientific computing.
- Experience working with embedded compute platforms, high-bandwidth data paths, or hardware-software co-design.
- Familiarity with structured engineering processes, including requirements, architecture, design reviews, verification, and traceability.
- Experience using Git and lifecycle or work-management tools to manage code, documentation, reviews, and technical activities.
- Clear written and verbal communication skills, with the ability to explain complex technical subjects and work with international, multidisciplinary teams.
