Edge ML Engineer - Real-Time Biosignals for Wearables

Almaz Capital; Graz; On-site; EUR 45,000 - 60,000; Full time

Benefits offered by this job

Lunch subsidies

Free parking

Canteen

Snack buffet

Well-being subsidies

Summer childcare subsidies

Job summary

USound in Graz, Austria, seeks a Senior Machine Learning Engineer to lead real-time AI models for acoustic biosignal analysis on edge devices in health wearables.

You will design ML models (CNN, LSTM,Transformers), deploy on TensorFlow Lite, ensure robustness, and mentor engineers while collaborating with firmware and backend teams. This role emphasizes edge AI, privacy compliance, and scalable deployment.

Qualifications

• Master’s or PhD in CS/AI/EE or Embedded Systems.
• Strong background in deep learning and time-series analysis.
• 6+ years in ML/AI focusing on biosignals.
• Experience deploying ML on mobile/embedded devices.
• Knowledge of acoustic biosignals (APG, OAE).
• Experience with edge deployment and security/compliance (GDPR/HIPAA).

Responsibilities

• Design and lead development of advanced ML models (CNN, LSTM, Transformers) for extracting HR, HRV, Pulse Wave Velocity, and Cardiac Output.
• Ensure robustness of models against noise, motion, and device variability.
• Drive mobile & edge deployment efforts (TensorFlow Lite, quantization, OTA updates).
• Mentor less-experienced engineers and collaborate with firmware, SDK, and backend development.
• Contribute to security and compliance strategies (GDPR/HIPAA).

Skills

Deep learning

Time-series analysis

Model deployment

Edge ML

Signal processing

Mobile/embedded deployment

Acoustic biosignals

Education

Master’s or PhD in CS/AI/EE/Embedded

Tools

TensorFlow Lite

OTA updates

TensorFlow Federated (TF Federated)

Quantization

Job description

USound in Graz, Austria, seeks a Senior Machine Learning Engineer to lead real-time AI models for acoustic biosignal analysis on edge devices in health wearables.

You will design ML models (CNN, LSTM,Transformers), deploy on TensorFlow Lite, ensure robustness, and mentor engineers while collaborating with firmware and backend teams. This role emphasizes edge AI, privacy compliance, and scalable deployment.