🛠 Tech Stack

💼 About This Role

You'll design and implement deep learning models for computer vision tasks, focusing on model compression and efficient architectures for edge systems. You'll read and implement ideas from top conferences like CVPR and NeurIPS. This internship offers hands-on research experience and mentorship from experienced researchers.

🎯 What You'll Do

• Design and implement deep learning models for computer vision tasks.
• Research and experiment with CNNs and Vision Transformers.
• Apply model compression techniques such as knowledge distillation.
• Perform quantization-aware training and post-training quantization.

📋 Requirements

• Solid foundation in Deep Learning (preferably PyTorch).
• Experience with CNNs and/or Transformers (academic or project).
• Understanding of bias–variance trade-offs and generalization.
• Familiarity with optimization fundamentals and basic probability.

✨ Nice to Have

• Experience with ONNX, TensorRT, TFLite or LiteRT.
• Familiarity with experiment tracking tools (e.g., W&B, MLflow).
• Prior participation in research projects or conference work.

🎁 Benefits & Perks

• 🧑‍🏫 Mentorship from experienced researchers and engineers.
• 📄 Opportunity to contribute to publications or conference submissions.
• 🧪 Hands-on research experience in applied computer vision.
• 🖥️ Exposure to model optimization and edge deployment challenges.