🛠 Tech Stack

💼 About This Role

You'll develop high performance kernels for accelerating ML models at d-Matrix. You'll implement, test, and tune kernels, define reference implementations, and analyze performance. This role offers hands-on experience in hardware-software co-design for generative AI.

🎯 What You'll Do

• Implement high performance kernels in low-level languages
• Develop, test, and tune kernels for ML models
• Create and automate reference implementations and unit tests
• Analyze scalability, collect metrics, and troubleshoot bottlenecks

📋 Requirements

• Ability to implement high performance kernels in low-level languages
• Proficiency in Python and/or C++
• Solid background in ML model architecture (e.g., LLMs, CNNs)
• Experience with ML frameworks such as PyTorch and Numpy

✨ Nice to Have

• Previous internship in high performance computing or ML kernel development
• Familiarity with TensorFlow or additional ML frameworks
• Interest in hardware-software co-design

🎁 Benefits & Perks

• 💰 Paid internship at CA$40–$70/hour
• 🎓 Graduate-level research experience
• 🤝 Collaborative startup culture
• 🌍 Hybrid work in Toronto