DhanushKautilya Kammaripalle

About

Built and deployed LLM-powered features for a startup organizational management application, focusing on real-world deployment constraints like latency and cost. Implemented RAG with FAISS and improved retrieval quality by switching embedding models (OpenAI/Hugging Face) and fine-tuning embeddings on medical corpora for a medical-report UI feature. Uses LangChain and LangGraph to orchestrate multi-node LLM API workflows and evaluates systems with metrics like latency, cost per request, and error taxonomy.

Experience

Education

Key Strengths

• Production deployment of LLM features with latency and cost constraints
• RAG quality optimization via model comparison, chunking, and embedding tuning
• Fine-tuned embeddings on medical corpora to improve FAISS retrieval performance
• LLM orchestration using LangChain and LangGraph (multi-node graph workflows)
• Structured evaluation approach using latency, cost per request, and error taxonomy
• Ability to align non-technical stakeholders on feasibility, cost, and latency tradeoffs

Reference Highlights

• Excellent cross-team collaboration
• Very strong with non-technical stakeholders
• Bridges gaps between business expectations and technical feasibility
• Clear and detailed communicator
• Patient listener
• Handles hurdles effectively
• Proactive problem-solving (proposed workable approach)
• Business-focused and outcome-oriented
• Hands-on AI engineer who ships solutions to production
• Structured and pragmatic approach to technology and budget efficiency
• Strong at balancing performance, scalability, and cost
• Proactive in gathering requirements and clarifying constraints
• Strong cross-team collaboration
• Takes ownership and responsibility (setup, provisioning, monitoring)
• Stays current with emerging AI features and releases
• Clear, structured communicator with non-technical stakeholders
• Breaks down complex AI topics into straightforward explanations
• Helps align technical solutions with business expectations