Traineeship: Integrate Telemetry Profiler in CPU-GPU Framework

Exail; Moeskroen; Sur place; EUR 13 000 - 20 000; Plein temps

Résumé du poste

Exail Belgium, a high‑tech company, explores unmanned surface and underwater vehicles for mine detection and telemetry, based in Mouscron near Kortrijk. The role focuses on integrating a real‑time profiler into the SAS processing stack on an embedded platform.

You will work in an international team on heterogeneous workloads (CPU/GPU) with CUDA, C++ and Linux, contributing to steady performance and stability improvements on challenging projects.

Qualifications

• Proficient in C++ with object‑oriented design.
• Good command of Dutch or French; English acceptable in an international setting.
• Experience with CUDA or GPU programming is a plus.
• Familiarity with Linux (Ubuntu) and build tools like CMake; GTest is beneficial.

Responsabilités

• Integrate an open-source profiler into the SAS processing stack to map resource usage on a low‑power embedded system.
• Prototype real‑time remote telemetry and profiling for heterogeneous workloads (CPU/GPU).
• Collaborate with a team to resolve performance and stability challenges and propose solutions.

Connaissances

Dutch

French

English

C++

OOP

Teamwork

Initiative

CUDA

CMake

Linux

GTest

JIRA

Outils

CUDA

CMake

GTest

Linux

JIRA

Description du poste

Company Presentation

Exail is a leading industrial player in high-tech solutions for the civil and defence sectors.Exail Robotics Belgium develops and produces unmanned surface/underwater vehicles that detect, identify, and destroy sea mines or explosives. Thanks to our innovative "standoff" concept adopted by the Belgian and Dutch navies, we can significantly reduce the risks involved in mine hunting. We also develop our own sonars, which enable to view and detect objects on the waterbed.

Task description

Our Sonar projects contain many components from Command & Control,system state collection to heavy data processing. One of these components isour SAS (Synthetic Aperture Sonar) processing stack. This sonar data processingruns multiple concurrent threads that each have a heterogeneous workloads bothon the CPU and on the GPU (CUDA).

This all happens on a low power embedded system with limitedresources, thereby making performance and stability key. It's hard to get aclear view on what's going on exactly when, which stage is consuming whatamount of memory is there an under or overload of the GPU, etc...

To remedy this we want to leverage an open-source off-the-shelfsolution for real time remote telemetry and profiling. From the core thisprofiler supports heterogeneous profiling and give us deep statistics of howour code runs on the embedded platform.

Your task entails integrate this profiler (starting with our SASprocessing stack) to map out the resource usage of our processing as aprototype.

Required skills

• Good command of Dutch orFrench. Can have a conversation in English. You will work in an international environment.
• Knowledge of C++, experiencewith object-oriented programming.
• Being able to work in a team.
• Take initiative in resolving issues and proposing solutions.
• Experience with cmake, make,gtest and Linux (Ubuntu) is a plus
• Experience with larger softwareprojects (multiple repository, JIRA) is a plus
• Experience with CUDA theparallel computing API/library of NVIDIA is a plus

In Practice

• Duration: flexible, minimum 2months total.
• Physical presence on site is required. Mouscron is about a 15-minute drive from Kortrijk. By publictransport, our offices are 15 minutes by bike or bus from the train station.Occasionally, we can arrange a visit (and transport) to the Ostend factory whereour unmanned vehicles are built.