Principal Machine Learning Compiler Engineer

About the job

We are looking for exceptional talent and leadership to join Fast Growing Startup into Scalable Intelligence, the world’s first company developing Agentic Silicon for powering the future of AI. Responsibilities: • Design, implement and maintain compilers specifically designed for optimizing ML models. This includes translating high-level ML model descriptions into efficient mapping to our hardware architecture, optimizing performance metrics such as flop utilization, memory bandwidth, and memory capacity. This also includes Design and implement the backend compilers that optimize code for specialized hardware like vector processors and systolic arrays, crucial for accelerating ML workloads. Required Skills: • Deep understanding of ML compiler design and optimization techniques • Hands-on experience in MLIR, LLVM and C/C++ • In-depth knowledge of ML frameworks (PyTorch) and Python • Expertise in low-level programming and assembly language • Knowledge of computer architecture, specifically vector and systolic array designs • Experience with performance tuning and analysis Experience level – 10+ years