Sukumar Raghavan

• • Designed and implemented RAG pipelines integrating various LLMs (including instruction-tuned models) with vector databases, improving response accuracy by 35%, and enabling citation capabilities while optimizing latency.

• • Led the development of ContagionNET product to detect viral load of COVID 19 using computer vision pipelines and deep learning models with the focus in scalability coordinating the distributed team across the globe that secured ~$20 million contract for the company to fight the pandemic.

• • Developed comprehensive model explainability frameworks using SHAP, feature importance analysis, and interactive visualization techniques, increasing model adoption rates by 40%.

• • Architect end-to-end AI/ML solutions, with a strong focus on advanced LLM applications, autonomous agentic AI workflows using MCP toolset, vLM embeddings computations and robust agentic RAG pipelines to drive real world business impact for clients across diverse sectors.

• • Designed intelligent agentic AI workflows to automate knowledge retrieval and reasoning for B2B clients, accelerating business impact.

• • Continued open-source contributions to prominent ML libraries (e.g., scikit learn, FairMOT, tensorzero), demonstrating ongoing technical leadership and commitment to AI community advancement.

Involved in developing the back end for the Private Banking Wealth Management project for the mobile banking 2.0 app for SCB.