Role Overview:
Experienced Data Scientist with a strong background in Microsoft Fabric and related Azure technologies, capable of transforming raw data into actionable insights. The ideal candidate will possess advanced skills in data science, feature engineering, machine learning model development, and data engineering, with hands-on expertise in Azure Machine Learning, Spark, and Python. In addition to technical expertise, the candidate should bring domain knowledge in wealth management marketing data to ensure that analytics and models align with industry-specific requirements.
Key Responsibilities:
- Ingest, clean, and analyze raw structured and unstructured datasets within Microsoft Fabric and One Lake environments.
- Perform feature engineering, data enrichment, and transformation to prepare datasets for modeling.
- Design, build, and deploy machine learning models in Fabric Data Science, Azure Machine Learning for predictive analytics, prospect identification, targeting, segmentation, personalization, campaign performance and other business use cases.
- Implement end-to-end data pipelines using Fabric Data Engineering and Spark, ensuring scalability and performance optimization.
- Write high-quality Python code for data preprocessing, model training, evaluation, and automation workflows.
- Apply statistical analysis and data visualization techniques to generate insights and communicate findings effectively to business stakeholders.
- Collaborate with cross-functional teams including Marketing, Business Intelligence, and IT to align solutions with business objectives in the wealth management domain.
- Work with marketing datasets (e.g., campaign engagement, lead scoring, client segmentation, conversion tracking, consumer profiles etc.) to support targeted outreach and performance measurement.
- Ensure compliance with data governance, privacy, and regulatory requirements in financial services analytics.
Required Skills & Experience:
- Strong hands-on experience with Microsoft Fabric Data Science and Data Engineering workflows.
- Proven expertise in data analysis, cleaning, and preprocessing of large-scale datasets.
- Solid track record in feature engineering and building machine learning models for production.
- Hands-on experience in Azure Machine Learning environment, including pipelines, model deployment, data drift, model drift and monitoring.
- Proficiency in Spark for distributed data processing and Python for advanced analytics and automation.
- Working knowledge of SQL for data querying and manipulation.
- Exposure to marketing data from the wealth management domain, including customer lifecycle analytics, segmentation, and campaign performance.
Preferred Qualifications:
- Familiarity with RAG (Retrieval-Augmented Generation), AI-powered personalization, or recommendation systems.
- Knowledge of predictive audience modeling or conversion prediction in financial services.