I architect enterprise-scale solutions at the intersection of Cloud Infrastructure, Intelligent Automation, and AI

Presents EvoGraphCoder, an evolutionary graph-reasoning framework that represents source code, dependencies, and commit history as a relational graph. Combines multi-agent evolutionary reasoning with persistent cross-release memory to generate and refine code repairs over multiple cycles, improving patch quality and robustness for reliable, explainable AI-assisted software maintenance.

Presents ScalePulse, a combinatorial large language model framework for identifying and resolving scalability constraints in distributed software systems.

This paper presents a novel approach to cloud observability using LLM-powered dynamic knowledge graphs for real-time monitoring and analysis of cloud infrastructure.

Introduces PerfSpark, a framework that leverages Large Language Models to intelligently monitor and diagnose runtime performance degradation in distributed systems.

Presents BugBlaze, an explainable AI framework designed to detect and predict latent software defects before they manifest in production environments.

Introduces ResolveLLM, an intelligent framework that uses large language models to automatically detect and resolve conflicts in collaborative software development environments.

Develops a comprehensive dataset and benchmark for detecting AI washing in marketing, promoting transparency and compliance in AI technology claims.

Proposes TrustGraph, a heterogeneous graph neural network for dynamic zero-trust policy enforcement in microservices architectures, enabling adaptive and context-aware security decisions.

Examines the evolution from traditional OCR to Intelligent Document Processing (IDP), demonstrating how AI-enhanced RPA transforms banking document workflows with significant gains in accuracy, speed, and compliance.