Senior Machine Learning Engineer

Qualifications and Experience:  

• 4+ years of ML engineering experience, preferably in biosignals, wearables, IoT, or health analytics

• Experience deploying ML models in production 

• Experience in dealing with various preprocessing and ML modelling problems

• Bachelor’s or Master’s degree in Computer Science, AI, Electrical Engineering, Data Science, or related fields

Key Skills and Competencies:

• Expert in ML/DL modeling, especially time-series and biosignals 

• Strong understanding of ML architectures such as CNNs, RNNs, Transformers, attention models, and traditional ML 

• Strong understanding of preprocessing techniques for ML such as dataset splitting, normalization, standardization, and feature engineering 

• Ability to deploy local and scaled models in production • Ability to deploy ML domain adaptation techniques such as finetuning, transfer learning, cross validation, adversarial training, …etc.

• Ability to build ML model pipelines such as training, inference, development iteration, and evaluation 

• Strong Python skills and experience with PyTorch/TensorFlow/NumPy

• Experience with real-time inference constraints (latency, power, memory)

• Familiarity with cloud ML pipelines (training, versioning, deployment, monitoring) 

• Understanding of medical device validation and reliability considerations

Language Requirements

• English (fluent written and verbal) – Mandatory
• Arabic (fluent written and verbal) – Mandatory

The Senior Machine Learning Engineer is responsible for designing, developing, and deploying advanced ML models across NEXA wearable medical and wellness platforms. This includes working with physiological biosignals (EEG, EOG, ECG, motion, ..etc.), creating real-time inference systems for edge hardware, and building robust cloud/IoT ML pipelines. The engineer will lead the full ML lifecycle — data acquisition, preprocessing, feature engineering, modeling, validation, optimization, deployment, monitoring — while ensuring models meet medical-grade reliability, safety standards, and real-world usability. This role also involves mentoring junior engineers, setting ML standards, and collaborating closely with hardware, embedded, software, and compliance teams.

1. ML Research, Modeling & Algorithm Development 

• Develop and improve ML models for bio signal analysis (EEG/EOG/ECG/IMU), anomaly detection, classification, prediction, and event detection 

• Work with different analysis and feature engineering techniques such as STFT, DWT, spectral analysis, temporal models, deep learning architectures, and signal enhancement techniques

• Design real-time, low-latency inference pipelines optimized for wearable devices • Conduct modelling experiments, transformations pipelines, and performance evaluations 

• Create robust, generalizable ML solutions across varied biosignal conditions and patient profiles

2. Signal Processing & Preprocessing Pipelines 

• Build local and scalable preprocessing workflows for noise removal, artifact correction, filtering, normalization, and segmentation 

Implement domain-specific DSP pipelines for EEG/EOG/ECG (ICA, ASR, band-pass f iltering, spectral transforms, etc.) 

• Develop adaptive, streaming-compatible preprocessing algorithms for real-time inference 

• Work with hardware and embedded teams to map preprocessing onto microcontrollers or neuromorphic chips

3. Edge & Embedded ML Deployment 

• Optimize models for microcontrollers, neuromorphic architectures, and low-power chips 

• Quantize, prune, compress, and accelerate models using techniques such as QAT, ONNX optimization, and neuromorphic conversion

• Collaborate with firmware teams to integrate ML models into wearable devices 

• Ensure latency, memory, and power requirements are met for continuous monitoring

4. Cloud, IoT & Backend ML Pipelines 

• Build cloud-side ML pipelines for large-scale data ingestion, training, evaluation, and re-training 

• Develop systems for telemetry-based analytics, trends, anomaly detection, and personalized modeling 

• Collaborate with backend teams to expose ML capabilities through APIs and cloud microservices 

• Implement monitoring dashboards for model drift, reliability, and real-world performance

5. Compliance, Safety & Medical-Grade Reliability 

• Ensure ML models comply with medical device expectations (consistency, transparency, explainability) 

• Maintain documentation required for regulatory submissions

• Validate ML performance under diverse physiological and environmental conditions 

• Work with QA and compliance to support verification & validation (V&V) activities

6. Cross-Functional Collaboration 

• Partner with hardware engineers on signal quality, sensor performance, and data characteristics

• Collaborate with embedded engineers to map models onto edge platforms 

• Work with software/mobile teams to integrate ML into user-facing products

• Coordinate with data engineers on datasets, pipelines, storage, and tooling

• Support product teams in defining data- and ML-driven user features

7. Mentorship & Technical Leadership 

• Mentor junior ML engineers and fresh graduates 

• Review code, research, experiments, and documentation 

• Establish best practices for data handling, version control, experiment tracking, and model governance

• Lead internal ML knowledge-sharing sessions, reading groups, or workshops 

• Guide the team on solving complex model challenges and design decisions

8. Agile Methodologies & Tools 

• Work in agile engineering environments with sprints, standups, and iterative planning 

• Use ML tooling such as: o PyTorch / TensorFlow o MNE / SciPy for signal processing o Weights & Biases, MLflow for experiment tracking 

• Use collaboration platforms (Jira, Confluence, Git, Notion)

• Maintain documentation for models, experiments, and reproducibility