Description

Requirements:

• Proficiency in Python, PySpark, and Databricks for large-scale data processing and ML development.
• Strong experience with scikit-learn, PyTorch, TensorFlow, and Hugging Face libraries.
• Proven background in recommendation systems, semantic search, or customer personalization models.
• Experience in feature engineering, EDA, model evaluation, and MLOps workflows.
• Familiarity with A/B testing frameworks and model observability practices.
• Strong collaboration and communication skills to work effectively.

Responsibilities:

• Build, test, and deploy recommendations, personalization, and predictive models that power digital experiences across banners.
• Develop end-to-end ML pipelines from data preparation and feature engineering to model training, evaluation, and production inference.
• Leverage Hugging Face Transformers, embedding models, and semantic search techniques to enhance product relevance and contextual understanding.
• Explore generative AI and retrieval-augmented generation (RAG) approaches for product matching, search, and personalization.
• Collaborate with MLEs to productionize models and ensure scalable, monitored, and retrainable ML systems.
• Partner with Data Engineers to design efficient data flows and maintain clean, versioned datasets for model consumption.
• Work with Data Science Leads and business stakeholders to define success metrics, design A/B experiments, and translate insights into data-driven actions.
• Contribute to shared best practices, documentation, and continuous improvement of ADUSA's advanced analytics ecosystem

Key Skills

Education

Bachelor's degree