Description

You will migrate XGBoost machine learning models from Java to Python and validate the accuracy of the new implementations against legacy benchmarks.

This role is remote.

Responsibilities

• Interpret data transformation logic and validate feature pipelines from existing Java implementations.
• Ingest model input data from parquet files using PySpark and pandas to reproduce training and scoring workflows.
• Run Python-converted models on historical datasets and validate output metrics against Java model benchmarks.
• Collaborate with model validation teams to review performance and explain metric deviations.
• Design unit tests and validation scenarios for migrated model signoff readiness.

Required Skills

• 7-10 years of hands-on experience with Python for machine learning, specifically XGBoost, SciKit-learn, and NumPy.
• Proficiency in PySpark for reading, transforming, and analyzing large datasets stored in parquet format.
• Experience validating or reverse engineering ML models from business logic or legacy implementations.
• Exposure to Java-based ML libraries or understanding of how internals map across languages.
• Hands-on experience with Python frameworks for meta-modelling libraries.
• Familiarity with Java and Python.

Preferred Skills

• Experience with Java-based ML libraries.

Key Skills

Education

Any Graduate