Low-Power ML Systems Engineer – On-Device Inference

Qualcomm; Markham; On-site; CAD 154,000 - 223,000; Full time

Job summary

A leading technology firm in Markham, Canada, seeks a Machine Learning Engineer to deploy AI models on low power AI accelerators. Candidates should have a strong background in machine learning, proficiency in Python and C/C++, and the ability to optimize models for inference efficiency. The position offers a competitive salary range of $114,400.00 - $164,400.00, highlighting Qualcomm's commitment to employee success and well-being.

Benefits

Competitive annual discretionary bonus

Opportunity for RSU grants

Comprehensive benefits package

Qualifications

• Strong track record in machine learning research.
• Deep understanding of ML model architecture.
• Hands-on experience with quantization and reduced-precision inference.

Responsibilities

• Explore and prototype ML model architectures.
• Drive model-hardware co-design for low-power AI accelerators.
• Design and evaluate quantization techniques.

Skills

Machine learning research

Inference efficiency

Quantization experience

Python proficiency

C/C++ proficiency

Computer architecture knowledge

Education

Bachelor's degree in relevant field

Master's degree in relevant field

PhD in relevant field

Job description

A leading technology firm in Markham, Canada, seeks a Machine Learning Engineer to deploy AI models on low power AI accelerators. Candidates should have a strong background in machine learning, proficiency in Python and C/C++, and the ability to optimize models for inference efficiency. The position offers a competitive salary range of $114,400.00 - $164,400.00, highlighting Qualcomm's commitment to employee success and well-being.