Staff AI Compiler Engineer

About the Role

EnCharge AI seeks a highly skilled Staff/Principal AI Compiler Engineer to lead efforts in developing and optimizing graph compilers tailored for cutting-edge AI and ML workloads. You will collaborate with hardware architects, researchers, and developers to enhance performance, optimize computation graphs, and enable efficient model deployment on EnCharge's Inference Accelerators.

Key Responsibilities

• Architecting, designing, and implementing optimizations for AI model execution on graph compilers to improve performance, reduce latency, and maximize hardware utilization.
• Collaborating with ML researchers, hardware engineers, and software developers to design and deploy AI models while addressing hardware-specific challenges.
• Focusing on performance optimizations for neural network models including layer fusion, operator fusion, and graph-level transformations.
• Developing compiler optimizations that convert high-level AI models from frameworks like TensorFlow and PyTorch into intermediate representations (IR).
• Implementing parsing, semantic analysis, and IR generation for deep learning frameworks.
• Researching and integrating the latest advancements in compiler design, ML model optimization, and hardware acceleration.
• Providing leadership, mentorship, and technical guidance to a team focused on graph compiler optimizations.