PROJECT INTEGRATION
Jev AI
Integrated into the current project as part of an evolving AI toolkit.
AI ARCHITECT & PLATFORM ENGINEER
Hello, I’m Sushant.
Intelligent systems.
Built for reality.
I turn complex data and AI problems into reliable production systems. A decade of building at the intersection of intelligence, infrastructure, and scale.
IIT Bombay · M.TechBased in Bangalore, India
SYSTEM / OVERVIEWv.01
DESIGNED FOR PRODUCTION
AI SYSTEMS / DATA PLATFORMS / OPEN SOURCESCROLL TO EXPLORE
ENGINEERING EXPERIENCE AT
GoogleGoldman SachsAngel OneAmagiSlintelPersistent
01 SELECTED WORK
From architecture to impact.
Real-time decisioning
Real-Time Ad Decisioning Platform
AI-powered real-time ad optimization system for streaming media, processing millions of ad decisions per second.
Read case studyApplied AI
B2B Intent Intelligence Platform
NLP-powered system for analyzing customer behavior and generating actionable intelligence for B2B sales teams.
Read case studyApplied AI
Enterprise Natural Language Analytics Platform
Building a system that translates natural language questions into SQL queries for intelligent data access.
Read case study02 TECHNOLOGY & EXPLORATION
A toolkit that keeps evolving.
Agent orchestration, model serving, and the data infrastructure behind them. Jev AI is now integrated into the current project.
AGENT SYSTEMS
Connected intelligence
Orchestrating agents, connecting tools, and building retrieval workflows with context.
MODELS & OPERATIONS
From model to service
Serving models, running local inference, and tracking the experiments behind production AI.
PLATFORM FOUNDATIONS
Infrastructure that holds up
Streaming data, containerized workloads, and observable services built to work together.
BUILDING IN THE OPEN
OpenCode & the homelab.
AI coding agents, MCP tooling, and self-hosted infrastructure. Where ideas become working systems.
03 THE ENGINEER BEHIND THE SYSTEMS
Curiosity drives it.
Engineering delivers it.
I’m Sushant Shambharkar, an AI architect and tech lead. My work spans real-time decision platforms, NLP, distributed systems, and production ML across finance, cloud, and AdTech.
I care about the entire system: the data that feeds it, the infrastructure that runs it, and the people it serves.
More about me10+years in engineering
30+engineers mentored
IIT BombayM.Tech, Computer Science
Build for the real world.
Reliability, latency, and graceful failure are part of the architecture from day one.
Treat AI as a system.
Good models need good data, thoughtful retrieval, evaluation, and observable infrastructure.
Make the impact measurable.
Instrument first. Establish a baseline. Improve what matters to the people using the system.
04 FIELD NOTES
Thinking out loud. Building in public.
RAG / LLM · 2 min read
Building Production RAG Systems: Lessons from the Trenches
A deep dive into building retrieval-augmented generation systems that actually work at scale, covering architecture decisions, embedding strategies, and production pitfalls.
Agentic AI / LLM · 2 min read
Agentic AI: From Research to Production
How to take agentic AI systems from research prototypes to production deployments with proper reliability, monitoring, and observability.
project /
OpenCode AI AgentLET’S BUILD SOMETHING THAT MATTERS