Seeking an experienced AI Compiler Engineer to develop and optimize graph compilers for advanced AI and ML workloads.
Collaborate with hardware architects and AI researchers to enhance performance, reduce latency, and improve hardware utilization for inference accelerators.
Design compiler optimizations such as layer and operator fusion, graph transformations, and IR generation from frameworks like TensorFlow and PyTorch.
Research and integrate latest compiler and hardware acceleration advances.
Provide technical leadership and mentorship to engineering teams.
Qualifications include 3+ years in compiler development, proficiency in AI graph frameworks (MLIR, Torch-FX), solid understanding of hardware architectures, neural network operators, and programming languages like C++ and Python.
Strong communication, team leadership, and open-source contributions are a plus.
This role spans locations including U.S., Canada, Germany, Norway, and India.