At DeepTechCollab, I built independent RAG pipelines, multi-agent systems, and an LLM evaluation framework to validate AI output quality. I also configured AI/ML training lab infrastructure and delivered workshops on AI/ML, GenAI, and Agentic AI.
At Macrometa, I designed and maintained unit, integration, and end-to-end test suites using Pytest and Playwright across microservices. I integrated automated testing into Jenkins CI/CD pipelines and owned defect tracking through remediation coordination and release acceptance sign-off.
On my Multi-Agent Research Intelligence Platform project, I built a LangGraph- and LangChain-based system coordinating five specialized agents, with a hybrid RAG pipeline and safety guardrails. I also created an AI test-case generation prototype using locally hosted Phi-3 and LLaMA models via Ollama.
