Hi, I'm
Naveen Vivek
I build AI agents and the infrastructure they run on, and write down what I learn along the way.
Senior AI Engineer in Singapore. Twelve years of backend engineering at JP Morgan, Oracle, TCS and Crédit Agricole, and the last two spent on GenAI, agents and the platforms underneath them.
What I work on
From the agent at the top down to the platform underneath.
Agents
Multi-agent systems, tool calling, MCP and LangGraph workflows that take real actions.
- SonarQube auto-fix agentProject
- JobRadarProject
Sandboxes and runtimes
Where agent-written code runs, and how to keep it from reaching things it should not.
Inference
KV cache, serving engines, fine-tuning, and getting useful speed out of GPUs.
- KV Cache VisualizerProject
- Fine-tuning on a home GPUProject
Developer platforms
Kubernetes, CI/CD and rolling out AI tooling to the engineers who use it every day.
Latest writing
The first article is on its way
It's about sandboxing the code AI agents write. Follow along on LinkedIn or subscribe to the RSS feed.
Selected projects
All projects- SonarQube auto-fix agentA hackathon-winning agent that reads SonarQube findings and proposes code fixes on its own.AWS BedrockLangGraphSonarQube
- KV Cache VisualizerAn animated explainer of how the KV cache works during LLM inference.
- GitHub Copilot rollout at Crédit AgricoleLed the adoption of GitHub Copilot across more than 200 developers.GitHub Copilot