nitinware - Overview

⭐ Hey, I'm Nitin Ware

Building AI Infrastructure • Scaling Kubernetes • Helping Developers Ship Reliable Systems


🧩 What I Do

I'm a Lead Engineer at Salesforce specializing in AI/ML infrastructure, Kubernetes-based model serving, and high-reliability distributed systems.

I spend most of my time:

  • 🚀 Building large-scale AI platforms that power millions of predictions
  • ⚡ Designing high-performance model execution runtimes
  • 🛰️ Improving service mesh, observability, caching & traffic reliability
  • 📚 Writing educational content that helps engineers solve complex infra problems
  • 🤝 Supporting the developer community through clear examples, diagrams, and tutorials

🌟 Why I Love Contributing

I believe complex infrastructure concepts should be simple, accessible, and enjoyable for every developer.

My work focuses on:

  • Teaching Kubernetes, Istio, Redis, and AI inference in a hands-on, practical way
  • Breaking down advanced systems into clear, visual explanations
  • Sharing reusable patterns for scaling distributed systems reliably
  • Helping teams adopt MLOps, LLM runtimes, and agentic AI
  • Building knowledge that benefits entire engineering communities, not just one team

🚀 Highlights

  • 🔧 18+ years building production systems across Salesforce, Home Depot, Bank of America, Morgan Stanley
  • 📦 Architected multi-tenant cache systems, high-scale model serving, and execution graphs
  • 📘 Published technical articles for DZone
  • 🧭 Known for creating practical tutorials on Istio, Kubernetes traffic, Ollama, Redis, and AI infra
  • 🛠️ Contributor & supporter of the Kubernetes ecosystem and related infra tooling
  • 🧠 Active member of IEEE & ACM, passionate about developer education

🌱 Currently Working On

  • Agentic AI systems & distributed runtimes
  • Green DevOps (energy-aware autoscaling, Kepler, Scaphandre)
  • Local LLMs & hybrid inference strategies
  • AI traffic management with Istio + Envoy
  • Developer-first education for Kubernetes & AI infra

🧰 Languages & Tools


📝 Latest Writing

I regularly publish deep-dive articles on:

  • Kubernetes traffic engineering
  • AI/ML model serving
  • Local LLMs & inference optimization
  • Service mesh reliability (Istio/Envoy)
  • Distributed caching strategies
  • AI infrastructure sustainability

If you’re building production systems, I write for you.


📫 Connect With Me