Join Amazon's Annapurna Labs as a Senior Machine Learning Kernel Engineer focusing on deep learning performance. Collaborate to design high-performance compute kernels for cutting-edge ML workloads.
As a key member of the Acceleration Kernel Library team, you will contribute to optimizing ML models on Amazon's powerful Inferentia and Trainium accelerators. Your expertise in low-level optimization and system architecture will facilitate creative solutions and maximize performance. This role requires engagement across various teams to enhance kernel optimization techniques and work closely with customers for effective machine learning enablement.
Key Responsibilities:
• Design and implement high-performance compute kernels • Analyze kernel performance across multiple Neuron hardware generations • Conduct performance analysis using profiling tools • Implement compiler optimizations and collaboration across teams • Provide direct customer support for ML model optimization
Requirements: • 5+ years of professional software development experience • 5+ years of programming in any software language • Experience leading design or architecture for systems • Proven mentorship experience in tech leadership • Proficient in ML accelerator architectures and optimizations
Elevate ML workloads at Amazon through high-performance kernel engineering and innovative solutions. #J-18808-Ljbffr