Embedded AI Engineer

About the Role 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. This role sits at the intersection of AI, embedded systems, and silicon — converting trained models into highly efficient on-device inference pipelines for battery-powered and always-on edge applications across vision, audio, activity, and time-series domains. Responsibilities Deploy AI models onto resource-constrained, proprietary SoC designs Optimize models across memory, power, and latency dimensions Execute model quantization at INT8 or lower precision Map neural networks to microcontrollers, DSPs, and AI accelerators Build inference pipelines in bare metal or Zephyr OS (advantageous) Validate embedded inference outputs against Python reference models Diagnose and resolve numerical mismatches between floating-point and quantized inference Tune memory layout, buffer reuse strategies, and tensor ordering Work closely with hardware and firmware engineering teams Requirements Solid grounding in machine learning fundamentals Practical experience deploying AI on embedded or edge hardware Strong proficiency in C/C++ (embedded context) and Python Hands-on experience with quantization techniques — PTQ or QAT Familiarity with memory-constrained system design Demonstrated ability to optimize for latency, memory footprint, and power draw Bonus Skills Exposure to TensorFlow Lite Micro, TVM, CMSIS-NN, or ONNX Runtime Knowledge of RISC-V architecture or custom AI accelerator design Experience with edge sensors — audio, IMU, vision, or wearables Background in power profiling and power optimization workflows Agile development exposure Why Join Work directly on production silicon and real edge-AI systems Build AI designed to run for months or years on battery power Direct collaboration with chip architects and systems engineers End-to-end ownership from model training to silicon deployment High-impact position within a fast-moving deep-tech environment