Apply deep learning and low-bit quantization skills during an in-person internship at STMicroelectronics in Toronto, Canada. Reduce model size and inference latency.

As a Deep Learning Research Intern, you will develop quantization techniques for deep learning models and analyze accuracy trade-offs. The work includes TensorFlow or PyTorch, Python, neural network architectures, and mixed-precision research. You will document experiments and results for internal teams and stakeholders.

Key Responsibilities:

- Develop low-bit quantization techniques for deep learning models
- Reduce model size and inference latency without compromising accuracy
- Analyze quantization performance and accuracy trade-offs
- Research mixed-precision quantization methods and improvements




- Document methodologies, experiments, and results clearly

Requirements:

- PhD or master’s degree in a related engineering field
- Experience with TensorFlow, PyTorch, or similar frameworks
- Hands-on experience with QAT and PTQ quantization
- Proficiency in Python; familiarity with C++ is a plus
- Understanding of neural network architectures and training processes

Bring deep learning, Python, and quantization expertise to STMicroelectronics research in Toronto, focused on effective model performance.

#J-18808-Ljbffr

📌 Deep Learning Quantization Research Intern (Toronto)
🏢 STMicroelectronics
📍 Toronto