Data Science Lead Edge AI

Role & responsibilities

• Lead end-to-end development of Edge AI models: (Human activity recognition, fall

detection, predictive maintenance, anomaly detection, etc.)

• Architect lightweight models (e.g., TinyML, TFLite Micro) for microcontrollers and IoT

devices.

• Collaborate with hardware, embedded, and firmware teams for edge deployment.
• Use techniques like: (Model quantization, pruning, knowledge distillation, ONNX

conversion)

• Signal preprocessing (FFT, time-domain, sensor fusion)
• Drive data collection strategies for real-world edge use cases.
• Own model performance metrics: (Accuracy, latency, power consumption, memory

footprint)

• Mentor a team of ML engineers and scientists; review code and model pipelines.
• Stay up to date with trends in TinyML, edge computing, and AI acceleration.

Preferred candidate profile

• Lead end-to-end development of Edge AI models: (Human activity recognition, fall

detection, predictive maintenance, anomaly detection, etc.)

• Architect lightweight models (e.g., TinyML, TFLite Micro) for microcontrollers and IoT

devices.

• Collaborate with hardware, embedded, and firmware teams for edge deployment.
• Use techniques like: (Model quantization, pruning, knowledge distillation, ONNX

conversion)

• Signal preprocessing (FFT, time-domain, sensor fusion)
• Drive data collection strategies for real-world edge use cases.
• Own model performance metrics: (Accuracy, latency, power consumption, memory

footprint)

• Mentor a team of ML engineers and scientists; review code and model pipelines.
• Stay up to date with trends in TinyML, edge computing, and AI acceleration.