Description

You will build, train, and validate machine learning models for prediction, classification, and clustering to support NBA use cases.

Responsibilities

• Conduct exploratory data analysis (EDA) on structured and unstructured data to extract actionable insights.
• Develop vectorization and embedding pipelines using models like Word2Vec and BERT for semantic understanding.
• Implement Retrieval-Augmented Generation (RAG) workflows to enrich recommendations using internal and external knowledge bases.
• Apply NLP techniques such as NER, text classification, and topic modelling.

Required Skills

• 5+ years of experience in data science or a related field.
• Expertise in Natural Language Processing (NLP) tasks.
• Familiarity with vector databases (e.g., PostgreSQL with pgvector, FAISS, Pinecone, Weaviate).
• Sound understanding of supervised learning and classification algorithms.
• Experience with recommendation systems.
• Proficiency in Data Analysis.
• Experience with BERT models.
• Familiarity with PostgreSQL.

Key Skills

Education

Any Graduate