AI & Engineering
Building intelligent systems that can scale with judgment.
My engineering work connects platforms, data, AI, product thinking, operating models, and leadership. The goal is not only to adopt new technology. The goal is to build systems that compound capability over time.
The engineering lens
I started my career in technology in 1995, close enough to the code to understand how systems actually behave, and close enough to business problems to see why technical elegance alone is not enough.
Over the years, I have worked across product engineering, enterprise modernization, large delivery organizations, data platforms, digital transformation, and AI initiatives. This has taught me to look at engineering as a living system made of architecture, talent, process, incentives, governance, and decision quality.
AI as architecture
AI becomes useful when it is connected to real workflows, reliable data, product context, human review, governance, and measurable business outcomes. Without those foundations, AI remains a demo. With them, it becomes an operating capability.
My interest is in practical AI systems: AI-assisted engineering, structured data extraction, classification, summarization, search, analytics, knowledge workflows, and enterprise adoption patterns that can survive beyond the first prototype.
Platforms before acceleration
Most transformation work fails when organizations try to scale on weak foundations. I care deeply about the layers underneath visible output: architecture, integration boundaries, data quality, engineering practices, security, observability, and ownership.
At SpecialChem, this included platform modernization, product engineering, AI initiatives, vendor strategy, annual IT roadmaps, and engineering capability buildout, including re-platforming a large B2B specialty chemicals marketplace using MACH architecture.
What I focus on
01AI strategy
Moving from scattered experiments to a coherent AI roadmap grounded in data, workflow, governance, and business value.
02Engineering leadership
Building teams with technical depth, execution discipline, ownership, product thinking, and a clear operating cadence.
03Platform modernization
Turning legacy complexity into modular, resilient, observable platforms that make future change easier.
04Data foundations
Creating the data, search, analytics, and integration foundations required for intelligent products and AI systems.
How I think about engineering
Good engineering is not only about shipping faster. It is about making better decisions repeatedly. It is about creating systems where teams can see clearly, learn quickly, recover safely, and build with confidence.
That requires technical architecture and human architecture. The best systems give people clarity about what matters, where decisions belong, how quality is protected, and how learning compounds.
AI & Engineering writing
Selected notes on artificial intelligence, data platforms, engineering leadership, product systems, and modernization.
-

Prompt Injection: The Hidden AI Security Risk
A malicious instruction does not need to look like malware. It can sit quietly inside an email, a web page, a PDF, a spreadsheet,…
-

Forward Deployed Engineers: The AI Era’s Fastest Growing Tech Role
Every major technology wave creates new roles. The internet gave us webmasters. Cloud computing created DevOps engineers. Big Data created data scientists. Artificial Intelligence…
-

AI Is Making Developers Faster. But Is It Making Them Better Engineers?
I was reading a discussion among software engineers recently about AI-assisted coding. What stood out was not the excitement around productivity. It was the…
-

Connect TradingView Desktop to Claude on Windows: Setup Guide for Indian Markets
Turn your TradingView charts into a live, queryable surface for Claude. Ask in plain English, get analysis, scoring, Pine Script edits, and morning briefs…