The role involves developing advanced TinyML and embedded AI solutions for specific microcontroller and MPU platforms. The engineer will build cloud-based model translation infrastructure and optimize network inference for resource-constrained systems. Responsibilities include developing a service that converts machine learning models into efficient C/C++ implementations for deployment. The position requires working across the stack from neural network internals to low-level performance optimization. The engineer will contribute new ideas and improve both tooling and embedded implementation quality.

Candidates must possess a BS, MS, or PhD in Electrical Engineering, Computer Engineering, Computer Science, or a related field. A minimum of six years of experience in embedded systems software development is required. Proficiency in C, C++, and Python is necessary for this role. Applicants must demonstrate experience in deploying machine learning models to resource-constrained systems and possess a solid understanding of neural network internals.