# Machine Learning / Software Engineering Thesis Student - Efficient On-Device ML for AR
## Project Background
Join Snap Inc to explore how to combine modern deep learning with event-based and embedded processors for AR glasses. The project focuses on pushing the limits of what AR glasses can do on-device by exploiting temporal and spatial sparsity to achieve always-on perception within strict power budgets.
## What You'll Do
As a thesis student, you will define and drive a focused research direction in efficient on-device ML for AR:
- Design and prototype ML models tailored to AR use cases under embedded constraints (event-based vision models, lightweight CNNs/Vision Transformers, hybrid frame+event pipelines)
- Set up datasets and baselines relevant to AR tasks (detection, tracking, segmentation, gesture/interaction) and define evaluation metrics across accuracy, latency, memory usage, and energy
- Implement and train models in PyTorch, including data pipelines, training loops, and evaluation scripts
- Explore efficiency techniques such as sparsity, pruning, quantization (PTQ/QAT), or event-based representations
- Profile models under embedded-like conditions using simulators, profiling tools, or edge accelerators
- Communicate findings through ablation studies, thesis report, and reproducible codebase with pre-trained checkpoints
## Expected Outcomes
- Demonstrate proof-of-concepts on AR hardware (Spectacles)
- Deliver measurable improvements in runtime performance, efficiency, and adaptability
- Provide insights into model–system co-design for low-power, on-device ML
- Contribute to ML frameworks, tooling, or deployment strategies for embedded AR systems
- Produce high-quality thesis report with reproducible code and results
## Minimum Qualifications
- Currently enrolled in Master's program (Computer Science, Electrical/Computer Engineering, Artificial Intelligence, Robotics, or related field)
- Degree program allows Master's thesis/graduation project with external organization
- Strong background in linear algebra, probability, and optimization
- Deep learning fundamentals including backpropagation, regularization, and model architectures
- Hands-on experience training deep learning models for computer vision
- PyTorch (preferred) or similar framework experience
- Comfort implementing and training CNNs and/or vision transformers
- Proficiency in Python and standard ML tooling (NumPy, PyTorch, Git, experiment management)
- Interest in turning research results into practical applications