GOWRI SHANKAR ANANTHULA

About

ML/NLP practitioner who built a retrieval-augmented generation (RAG) system for large financial and operational document sets using Sentence-Transformers (all-mpnet-base-v2) and a vector DB (e.g., Pinecone), with a strong focus on retrieval evaluation and chunking strategy optimization. Experienced in entity resolution (rules + embedding similarity with type-specific thresholds) and in productionizing scalable Python data workflows using Airflow/Dagster and Spark.

Experience

Education

Key Strengths

• Built and iterated a RAG system over financial/operational documents to reduce manual review time
• Strong retrieval-quality optimization (chunking/overlap tuning; precision/recall evaluation)
• Pragmatic entity resolution approach combining rules + embeddings with validation-driven iteration
• Improves semantic search relevance using vector DBs and domain fine-tuning while managing overfitting risk
• Production-grade Python workflow design (modular ETL, orchestration, logging/monitoring, version control)
• Scales pipelines with distributed compute (Spark), partitioning, parallelization, checkpoints, and bottleneck monitoring
• Clear prototype-to-production decision-making based on stability across segments, cost, and operational readiness