Bhavana Anna

About

AI/ML engineer who has shipped production LLM and ML systems, including a RAG pipeline that ingested ~500k insurance/client documents to help adjusters answer questions faster and more consistently. Experienced in handling messy real-world document formats, tuning retrieval/chunking, and reducing latency via vector search optimization, precomputed embeddings, and caching. Also built orchestrated fraud-detection deployment workflows using AWS Step Functions and SageMaker, and partners closely with non-technical operations teams on NLP automation.

Experience

Education

Key Strengths

• Built and deployed a production RAG system ingesting ~500k client documents
• Strong unstructured document processing (scanned PDFs, handwritten notes, mixed-format text)
• Practical retrieval/chunking optimization via experimentation (overlap windows, embedding strategies)
• Performance tuning for large-scale RAG (profiling vector search bottlenecks, vector store/index optimization, precomputed embeddings, caching)
• Orchestrated end-to-end ML pipelines with AWS Step Functions (ingestion → features → training → evaluation → SageMaker deployment)
• Designed resilient workflows with retries and fallback paths for long-running/fragile stages
• Production-minded testing approach for AI workflows (component-level unit tests)
• Effective collaboration with non-technical stakeholders to translate operational needs into NLP requirements