Seasoned AI/ML Enabler Lead with 16.9 years of industry experience, including over 7 years specializing in Machine Learning, Data Science, and Generative AI. I have a proven track record of leading an AI/ML Innovation Lab for a major investment banking client with $300B in AUM, where I drove the deployment of ethical, scalable, and enterprise-grade AI solutions. My expertise lies in translating complex AI capabilities into actionable business strategies that align with high-level client goals and regulatory landscapes.
I specialize in designing and implementing sophisticated multi-agent architectures and Agentic AI workflows. My recent work includes developing a semi-automated ITOPs system using the Microsoft Agent Framework and a hierarchical ticket classification pipeline utilizing GPT-4o and semantic embeddings. I am proficient in orchestrating complex LLM systems with LangChain and LlamaIndex, ensuring taxonomic consistency and high-performance retrieval across diverse project domains.
My technical toolkit features advanced Retrieval-Augmented Generation (RAG) techniques, such as Reciprocal Ranking Fusion (RRF) and encoder-based re-ranker frameworks. I have extensive experience managing proprietary and open-source models on Amazon Bedrock, Azure OpenAI, and AWS SageMaker. To ensure production-ready reliability, I implement custom AI guardrails to mitigate prompt injection and utilize evaluation frameworks like RAGAS and FMEval for rigorous performance tracking.
Beyond technical architecture, I am a passionate mentor and advocate for Responsible AI, integrating drift detection and SHAP-based explainability into production pipelines. I have successfully democratized AI access within large organizations by building platforms like AlHub, which empowers non-technical users to leverage LLMs for document summarization and policy analysis. My leadership has consistently reduced model adoption timelines and improved operational efficiency, such as halving the time required for complex customer query resolutions