Are you the Internship / Master’s Thesis – Embedded AI we're looking for?
Our VALUES
Join EDGX
EDGX is a fast-growing Belgian spacetech company defining the compute layer of the space economy. That future starts with edge computers onboard spacecraft and scales to data centre nodes in space. We're making the building blocks for compute services in space.
Pioneering Expertise
We build deep, niche expertise with purpose: challenging assumptions, closing knowledge gaps, and letting genuine curiosity drive us ahead.
Focused Ambition
We pair a bold, shared vision with full ownership of our work, turning focused ambition into real results.
Collective drive
We share knowledge openly, lift each other up, and push each other to grow; because collaboration isn't just how we work, it's how we innovate.
backed by industry leaders
Shape the future of space infrastructure
We started just three years ago, and we're moving fast. EDGX is backed by imec.istart, the imec.istart Future Fund, and the Flanders Future Tech Fund through a €2.3M seed round, plus several ongoing ESA contracts. Our first two satellite demonstration missions launched in March 2026 on a SpaceX Falcon 9, with more sure to come. If you want to help define the future of the space industry, you'll feel right at home at EDGX. 🚀
job description
Internship / Master’s Thesis – Embedded AI
Key Responsibilities
Implement hardware-dependent knowledge distillation for a compact multispectral object-detection student, then run the compiled student on commercially available M.2 AI accelerators that can be plugged into our DPUs. In parallel, perform a trade-off study on knowledge distillation methods suited to this task.
The internship lasts 3 to 6 months and can start in January or February 2027.
• Train a compact multispectral object-detection student from a teacher model, with Hinton-style knowledge distillation as the baseline.
• Research and implement other knowledge distillation methods, and define a metric for how efficient the distillation process is.
• Compile and run your student on two M.2 accelerators: Axelera Embedded 110m and MemryX Cascade 100.
• Compare accuracy and throughput, assess toolchain usability, and recommend which hardware to use.
What you're bringing
• A bachelor or master student incomputer science or AI.
• Experienced in, or interested in, resource-constrained edge AI systems.
• Curious about model compressionand edge deployment.
• Eager to learn, even if you have not worked with knowledge distillation before.
What's in it for you?
• Hands-on experience with real edge AI hardware: two commercial edge AI accelerators and their software toolchains.
• Practical skills in knowledge distillation, quantisation and model compilation for edge deployment.
• A first-hand look at AI for space: fitting models into the tight power and compute budgets of onboard satellite processing.
• Exposure to multispectral Earth observation data, which is less common than standard RGB imagery.
• Join a fast-growing spacetech startup with a young, driven team and a dynamic, hands-on culture.
