Portfolio
Each case study follows the same structure: problem, context, ideation, solution, architecture, prototype, AI integration, workflow, impact and learnings.
Where work involved proprietary products, architecture and details have been generalized. No internal names, data or code appear anywhere on this site.
Flagship case studies
Quality + Infrastructure + AI
An infrastructure-aware test system that provisions environments, generates realistic repository data, holds a target CPU load and validates security scanning — with AI-assisted observability.
Performance + Infrastructure + AI
A Jenkins pipeline that deploys the product, runs Gatling load, collects CloudWatch data every minute, and uses an AWS Bedrock agent to write the performance report — and a root-cause analysis when issues appear.
AI-Enabled Automation · UI + API
Playwright UI + API automation powered by Claude, MCP and a self-hosted Weaviate knowledge layer — a retrieve, execute, validate and remember loop.
AI engineering & explorations
AI Application Engineering
Business data often requires technical SQL knowledge, creating a gap between natural-language questions and usable analytical answers.
Exploration · RAG
How can an LLM produce more useful answers when it is grounded in relevant external knowledge instead of relying only on its model knowledge?
Exploration · Engineering Workflow
How can AI become an engineering multiplier without turning the engineering process into uncontrolled AI-generated output?