Senior Data Science Engineer

We are looking for a skilled Data Scientist to collaborate with financial experts on the development and prototyping of machine learning algorithms that drive pricing optimization, forecasting, and business decision-making. You will leverage Python and modern data science libraries, working with large datasets provided as Parquet files in an Azure cloud infrastructure. Experience with the Kedro framework, the Azure platform, and financial sector challenges is highly valued. The ideal candidate is adept at building data pipelines, conducting advanced analytics, and communicating insights in a consulting environment.

Responsibilities:

• Collaborate with financial experts to understand business problems and frame them as machine learning tasks.
• Prototype, build, tune, and deploy machine learning models - especially gradient boosted tree models using LightGBM (preferred) and XGBoost to address price optimization, forecasting, and other financial decision processes.
• Perform feature engineering, data preprocessing, and model validation on large structured datasets provided in Parquet format.
• Analyze feature importance and interpret model results to drive actionable insights for clients.
• Develop reproducible data pipelines using Python, employing modular frameworks such as Kedro when possible.
• Validate model performance through experiment frameworks such as A/B testing and industry-standard metrics (e.g., RMSE, MAE, AUC).
• Collaborate within an Azure-based infrastructure to integrate models into operational workflows and support production deployment.
• Communicate findings and present actionable insights to both technical and non-technical stakeholders.
• Contribute to a collaborative team environment and support knowledge-sharing.

Requirements:

• Proven experience deploying end-to-end data science solutions, ideally within financial services or economic domains.
• Previous experience with Kedro for pipeline orchestration and modular data science development is a significant plus.
• Gradient Boosted Tree experience, hands-on familiarity with implementing, tuning, and deploying machine learning models based on the gradient boosting algorithm. Experience with LightGBM and/or XGBoost open source frameworks is a significant plus.
• Experience in building or deploying models within enterprise cloud environments (AWS, Azure).
• Exposure to working with automated machine learning tools and scalable data engineering platforms.
• Solid understanding of:
  • A/B testing methodologies - experiment design and statistical analysis (classical t-tests, zero inflated models, etc).
  • Revenue forecasting models (DARTS, prophet, sktime, etc).
  • Price Optimization (regression analysis and optionally linear programming).
• Advanced SQL skills and experience with data manipulation tools (e.g., Pandas).
• Experience working with parquet files and manipulating large structured datasets.
• Hands-on experience in Azure cloud environments (Databricks, Azure ML, Data Lake, etc.).
• Experience with CI/CD workflows (Continuous Integration / Continuous Deployment) for data science and machine learning projects, enabling automated model testing, integration, and deployment.
• Understanding of ETL/ELT processes and data pipeline orchestration
• Strong collaboration and communication skills, with the ability to interact with subject matter experts and clients
• Strong organizational skills with keen attention to detail.
• Excellent communication, analytical and interpersonal skills.
• English - Upper intermediate or Advanced.