Data Scientist

Duration: 6+ months
Location: On-site 3 days/week in Quincy, MA
Relocation Accepted: Yes
 
As a Senior Data Scientist, you'll play a key role in designing and scaling advanced machine learning and AI solutions that drive personalization, recommendations, and intelligent automation across. You'll collaborate closely with Machine Learning Engineers, Data Engineers, and Data Science Leads to turn data into business impact developing robust models, optimizing pipelines, and delivering measurable results that improve customer engagement and operational efficiency.

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.

Must have technologies:

• Python, Pyspark, Pytorch
• Experience with recommendation/personalization models
• Exposure to GenAI
• Databricks

26-00432