Skip to content

About

Enterprise engineer, building an AI architecture practice.

I'm Vikas Yadav, a software engineer based in India with 9+ years of building enterprise systems, mostly in Java and Spring.

Path

From freelance projects to enterprise platforms to AI.

  1. 2014

    First client work

    Freelance projects, from Java backends to storefronts and Android apps.

  2. 2017

    Full-time engineering

    Fullstack developer at Sanatan Digitizers, then Gradlic Solutions.

  3. 2019

    Teaching

    Trained a few hundred developers across Java, Spring, React and Android at a training institute.

  4. 2021

    Enterprise platforms

    Banking services for Canadian Tire Bank, then the Equifax credit data fabric and U.S. Bank.

  5. 2024

    AI in daily work

    From Copilot in the editor to Claude Code working as an agent on a production codebase.

  6. Today

    Engineering lead and AI architect

    Leading the India team on Vendavo's pricing platform, and building an AI architecture practice.

Background

Most of my career has been spent inside large platforms that can't afford to go down: the backend services behind banking applications for U.S. Bank and Canadian Tire Bank, the data fabric Equifax builds credit reports from, and today, as Engineering Lead at Ness Digital Engineering, Vendavo's enterprise pricing platform. Along the way I've upgraded a multi-tenant application four major Spring versions, built a purchasing-card service on AWS serverless to PCI DSS practices, and spent a lot of time on the unglamorous work of making systems talk to each other.

Since 2024, AI has become part of how I work every day. It started as GitHub Copilot in the editor, moved to an internal multi-model assistant at Ness, and is now Claude Code, used as an agent that reads and changes a production codebase rather than as autocomplete.

Why AI architecture

The hard part of enterprise AI is rarely the model. It's connecting it to the right data without leaking it, integrating it with systems that were never designed for it, proving it gives good answers, and getting a team to trust and use what was built. Those are engineering problems, and they're the ones I've worked on for my whole career.

So I'm building a practice around two things: helping businesses design and implement AI systems that fit what they already run, and helping engineering teams adopt AI-assisted development properly. I write up what I learn along the way, so clients can see how I think before we ever speak.

Teaching and building

Enablement work draws on time spent as a technical trainer, where I took a few hundred students through Java, Spring, React, the MERN and MEAN stacks and Android. Teaching is the fastest way to find out whether you really understand something.

I also build and run my own product, Udyamik, a multi-tenant platform for SMBs on Spring Boot, PostgreSQL row-level security and React. Owning a product end to end, from schema design to production incidents, keeps my advice grounded.

Working stack

Backend
Java, Spring Boot, Spring Security, Spring Data JPA, Spring Cloud, REST, GraphQL
Data
PostgreSQL, Redis and Valkey, Apache Beam on Google Cloud Dataflow
Front end
React, micro frontends, Tailwind
Cloud and ops
AWS (including serverless), Linux, Docker, Caddy, Jenkins, GoCD
AI
Claude Code, Claude API, MCP, RAG, agentic workflows, evaluation

Certifications

Contact

Have an AI initiative in mind?

Let's discuss the business problem, evaluate the opportunity and work out a practical implementation approach.