Data Scientist/ML Engineer - EU Remote - 6 Months

We are looking for a highly skilled Data Scientist/Machine Learning Engineer to join our growing data team, focusing on real-time anomaly detection within a modern Azure + Databricks ecosystem. You will play a key role in designing, building, and deploying scalable ML solutions that process streaming data and deliver actionable insights.

This is an exciting opportunity to work on cutting-edge data platforms and contribute to the full machine learning lifecycle-from experimentation to production.

Key Responsibilities

• Develop and deploy real-time anomaly detection models for streaming data environments
• Build and maintain end-to-end ML workflows using Databricks
• Manage the ML model lifecycle using MLflow, including tracking, experimentation, and deployment
• Design and maintain model serving endpoints for scalable inference
• Implement model versioning, testing, and performance tuning processes
• Apply statistical techniques (e.g., z-score normalization) for data preprocessing and feature engineering
• Use signal processing methods (e.g., FFT transformations) to enhance feature extraction and anomaly detection
• Collaborate with data engineers and platform teams to optimize pipelines within Azure Databricks

Required Skills & Experience

• Proven experience in anomaly detection, particularly in real-time or streaming scenarios
• Strong hands-on experience with Databricks-based ML workflows
• Expertise in MLflow for experiment tracking and lifecycle management
• Experience building and managing model serving endpoints
• Solid understanding of:
  • Model versioning and testing frameworks
  • Model performance tuning techniques
• Strong foundation in statistics and data preprocessing, including normalization techniques like z-score
• Familiarity with signal processing concepts such as FFT (Fast Fourier Transform)
• Experience working within an Azure + Databricks platform

Nice to Have

• Experience with large-scale streaming tools (e.g., Kafka, Spark Streaming)
• Knowledge of MLOps best practices and CI/CD for ML pipelines
• Exposure to production-grade monitoring and alerting systems for ML models