I have been building data and AI systems for more than eight years. I started with data engineering and data science, moved into search and NLP, and now work mostly on generative AI and agentic systems.

I currently lead the AI R&D Lab at Indexnine Technologies as Senior AI Architect. I am also Co-Founder and CTO of Order.law, an AI-native legal technology company. We started it after I built a proof of concept in fifteen days and we showed it to lawyers at the Bombay High Court.

Before that, I worked on search systems, NLP pipelines, model deployment, analytics, and data engineering at Simplifai Cognitive Services, Bajaj Finserv, and Avance Consulting. I have also worked on fine-tuning and deploying generative AI models where data security and limited infrastructure were real constraints, not points on a presentation slide.

My path into this work was not straightforward. I graduated from IIT Kanpur with a dual degree in 2015 and went to the University of Washington, Seattle for a PhD in Economics. I left after two quarters and joined IPAC, where I worked on political data and campaign strategy across Punjab, Uttarakhand, Uttar Pradesh, and Andhra Pradesh. After that, I taught IIT-JEE for about a year and a half before starting again as a data engineer.

That earlier work still affects how I think about AI. Economics made me look for incentives, and political campaigns taught me to distrust any model of the world that has not been tested on the ground. I am interested in the same gap in AI now: the gap between what works in a demo and what continues to work when real people, data, organizations, and constraints enter the picture.

I write about what I am learning while working through that problem: agentic systems, AI governance, AI-native engineering, legal technology, interfaces for software agents, and knowledge systems.

Elsewhere