全职 Embedded AI Engineer 工作, 薪水 up to SGD 4,500, FONTES SINGAPORE PRIVATE LIMITED West Region (Singapore) 公司招聘中 - Ricebowl

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