Working Student - Machine Learning

Master's thesis / graduation project in Machine Learning and Software Engineering focused on efficient on-device ML for AR applications on embedded and event-driven processors. You will explore how to combine modern deep learning with event-based and embedded processors to push the limits of what AR glasses can do on-device.

Key responsibilities:

• Design and prototype ML models tailored to AR use cases under embedded constraints (e.g., event-based vision models, lightweight CNNs/Vision Transformers)
• Set up datasets and baselines relevant to AR tasks (detection, tracking, segmentation, gesture/interaction)
• Implement and train models in PyTorch, including data pipelines, training loops, and evaluation scripts
• Explore efficiency techniques such as sparsity, pruning, quantization, or event-based representations
• Profile models under embedded-like conditions using simulators and profiling tools
• Communicate findings through ablation studies, thesis report, and reproducible codebase

Expected outcomes include proof-of-concepts on AR hardware (e.g., Spectacles), measurable improvements in runtime performance and efficiency, insights into model-system co-design, and a high-quality thesis report with reproducible code.