AI/ML - ML/HW/SW Co-Design Engineer, DMLI

The Data and Machine Learning Innovation (DMLI) team at Apple is seeking an AI/ML - ML/HW/SW Co-Design Engineer to work on achieving best-in-class performance and energy efficiency for neural network use cases. This role involves bridging the gap between ML and devices, working with ML, computer architecture, and SW teams to understand trade-offs in ML inference, and developing novel solutions for future ML workloads.

Key responsibilities include:

• Co-designing hardware and software solutions to improve efficiency of neural workloads at inference time
• Implementing features in simulation engines and compilers for next-gen accelerators
• Benchmarking and diagnosing performance bottlenecks of deep learning models
• Collaborating with partners across various stack levels, from Apps to Compilation, HW Arch, and Silicon Validation

The ideal candidate should have:

• A Bachelor's, Master's, or PhD in Electrical Engineering, Computer Science, or a related field
• 5+ years of experience in ML inference performance optimization (SW or HW)
• Proficiency in Python and working knowledge of C++
• Strong algorithms and coding skills for workload optimization
• Deep understanding of computer systems and HW/SW interactions
• Excellent communication skills and ability to analyze complex problems
• Experience with backend compilation, ML/HW/SW co-design, and performance optimization
• Familiarity with ML model efficiency techniques and their inference bottlenecks

This role offers an opportunity to work on cutting-edge AI/ML technologies at Apple, pushing the boundaries of performance and power efficiency for AI inference. Join a team of experts in ML, hardware, and software to shape the future of machine learning acceleration.