Unlock your potential as a Senior ML Accelerators Kernel Engineer at Amazon's Annapurna Labs. Focus on designing high-performance kernels specifically for deep learning operations on cutting-edge ML accelerators. As a cornerstone member of the Acceleration Kernel Library team, you'll engage in creating scalable performance solutions for our diverse client base.

This role prioritizes your deep technical skills in both hardware and software, pushing boundaries in AI acceleration while ensuring efficiency in machine learning workloads across platforms. Your collaboration with clients will ensure we're meeting their unique optimization needs. Key Responsibilities:

- Develop compute kernels optimized for ML applications
- Analyze and refine kernel performance across Neuron generations




- Utilize profiling tools for performance bottleneck resolution
- Execute various compiler optimizations to enhance capabilities
- Collaborate across teams for innovative solutions Requirements:
- 5+ years of qualified software engineering
- Strong leadership skills with experience mentoring teams
- Proven expertise in GPU optimization and accelerator architectures
- Proficiency in multiple programming languages
- Understanding of parallel programming techniques Shape the future of machine learning performance at Amazon through your innovation and engineering prowess.

📌 Senior ML Accelerators Kernel Engineer (Toronto)
🏢 Amazon
📍 Toronto