Embedded AI Engineer

We are looking for an Embedded AI Engineer to build, optimize, and deploy neural networks on ultra-low-power, memory-constrained SoCs and AI accelerators. 
You will work at the intersection of AI, embedded systems, and silicon, translating trained models into highly efficient on-device inference pipelines for battery-powered and always-on edge applications for vision, audio, activity and time-series applications. 

Tasks & Responsibilities 

• Deploy AI models on resource-constrained in-house design SoCs 

• Optimize models for memory, power, and latency 

• Perform model quantization (INT8 or lower) 

• Map neural networks onto microcontrollers, DSPs, and AI accelerators 

• Implement inference pipelines in bare metal or Zephyr OS (bonus) 

• Validate embedded inference against Python reference models 

• Debug numerical mismatches between float and quantized inference 

• Optimize memory layout, buffer reuse, and tensor ordering 

• Collaborate closely with hardware and firmware teams 

Requirements 

• Strong fundamentals in machine learning 

• Hands-on experience deploying AI on embedded or edge devices 

• Proficiency in C/C++ (embedded) and Python 

• Experience with quantization (PTQ or QAT) 

• Understanding of memory-constrained systems 

• Ability to optimize latency, memory footprint, and power consumption 

• Experience with TensorFlow Lite Micro, TVM, CMSIS-NN, or ONNX Runtime 

• Knowledge of RISC-V architecture or custom AI accelerators 

• Experience with edge sensors (audio, IMU, vision, wearables) 

• Familiarity with power profiling and optimization 

• Agile development experience