Building intelligent AI systems, LLM-powered tools, and multi-agent applications. 13+ years of engineering experience bridging deep automation expertise with cutting-edge AI.
With over 13 years building large-scale test automation systems across Capgemini, Adidas, RBS, UnitedHealth Group, and Xerox, I've developed a deep understanding of software quality at enterprise scale.
Now I'm channeling that engineering rigor into AI โ building multi-agent systems, LLM-powered developer tools, and intelligent automation that doesn't just test software but understands it.
My work sits at the intersection of AI and software engineering: using large language models to solve real problems in testing, code quality, data visualization, sprint analytics, and team productivity.
A cross-disciplinary toolkit spanning AI/ML, backend engineering, and quality automation.
Real tools solving real problems โ from multi-agent collaboration to AI-powered testing frameworks.
Real-time multi-agent collaboration platform where ChatGPT, Gemini, and Groq work together via a hub-and-spoke orchestrator. Supports sequential workflows and round-robin discussions with live streaming and syntax-highlighted code output.
AI test intelligence dashboard that integrates with Jira and GitHub to auto-generate test plans and test cases. Analyzes PR diffs and story requirements with LLM agents to identify impacted areas and export structured DOCX reports.
Comprehensive framework for detecting and evaluating hallucinations in AI-generated content. Generates test prompts, judges LLM responses for factual accuracy, and computes precision, recall, and F1 hallucination scores with batch processing.
Chrome extension that analyzes Jira sprint boards using GPT-3.5 to surface team health risks, workload imbalances, and actionable sprint recommendations. Exports shareable PDF reports directly from the extension.
AI-powered data visualization platform that transforms CSV data into professional interactive dashboards. Features natural language querying, intelligent chart-type recommendations, 6 built-in themes, and multi-format exports (PNG/PDF/CSV/Excel).
AI-powered accessibility regression tool that uses Vision LLM to compare two versions of a web page and detect new WCAG violations. CI/CD-ready for automated staging-to-production checks with interactive Plotly dashboards.
Model Context Protocol server that plugs into Claude Desktop to deliver instant Java code quality feedback. Runs Checkstyle, spell checking, Javadoc coverage, and naming convention analysis in under one second with emoji-categorized results.
A prompt engineering toolkit for crafting, testing, and optimizing prompts for LLM applications. Helps developers iterate quickly on prompt design with structured evaluation and versioning capabilities.
13+ years across global enterprises โ from financial services and healthcare to retail and technology consulting.
Leading automation strategy and framework design for enterprise clients. Building scalable CI/CD pipelines with Docker and Jenkins, and spearheading integration of AI-assisted testing tools into the QA workflow.
Developed end-to-end automation frameworks for Adidas e-commerce and internal platforms. Implemented API testing suites with RestAssured and integrated test reporting into the development pipeline.
Built robust test automation infrastructure for banking applications with 3500+ automated process queues. Designed REST API test frameworks and led migration of manual test suites to fully automated pipelines.
Automated functional and regression test suites for healthcare applications. Developed reusable test components using Selenium WebDriver and contributed to performance testing with JMeter.
Started career in software quality assurance, performing manual and exploratory testing on document management and print solutions. Built early automation skills with Selenium implementations.
Open to AI Engineer, SDET, and Senior QA Automation roles. Let's build something intelligent together.