Drive innovation as a Senior ML Kernel Performance Engineer at Amazon's Annapurna Labs. Leverage your skills to architect and implement high-performance kernels that optimize GenAI workloads on custom ML hardware.This position centers around building the Neuron SDK, crucial for accelerating deep learning applications. You will analyze and optimize ML function performance, collaborate with teams, and directly support customers in achieving efficient model enablement on AWS accelerators. This role blends technical depth with creative problem-solving in an agile development workplace.Key Responsibilities:
- Develop and implement efficient compute kernels for ML
- Analyze and enhance kernel performance across hardware generations




- Use profiling tools to uncover and fix performance bottlenecks
- Execute compiler optimizations for improved efficiency
- Partner with customers to optimize their machine learning modelsRequirements:
- 5+ years of professional software development experience
- 5+ years programming at least one language
- Proven design and architecture experience
- Background in mentoring or leading teams
- Expertise in accelerator architectures preferredJoin Amazon to make a marked impact on AI acceleration technologies.#J-18808-Ljbffr

📌 Amazon Senior Performance Engineer – Ml Kernel (Toronto)
🏢 Amazon Web Services (AWS)
📍 Toronto