Build, train, and validate ML models for NBA use cases.
Conduct EDA on structured/unstructured data.
Design A/B testing frameworks and monitoring pipelines.
Implement
Word2Vec, BERT
embeddings and
RAG workflows
with LangChain or Haystack.
Work with vector databases (
pgvector, FAISS, Pinecone, Weaviate
).
Collaborate with teams to deliver NBA strategies.
Required Skills:
Proficient in
Python
(pandas, NumPy, scikit-learn).
Strong in text embeddings, prompt engineering, and RAG pipelines.
NLP expertise (NER, text classification, topic modeling).
Knowledge of supervised learning and recommender systems.