I build AI systems
that survive production.
Multi-agent pipelines. Production infra. End-to-end delivery.
30K → 200K users. Prototype → stock exchange.
> routing to capability_layer...
What I Build
Multi-Agent Systems
Design and deploy production agent pipelines. Not wrappers. Full systems with memory, tools, routing, and evaluation.
Document Intelligence
High-recall RAG for complex unstructured docs. Built for compliance, finance, and enterprise domains where failure is not an option.
Voice AI & Real-Time
End-to-end voice pipelines — STT → LLM → TTS. Low-latency, stateful, handles real-world edge cases like interruptions and drift.
AI Infrastructure
From single server to Kubernetes. Canary deploys, Datadog monitoring, experimentation pipelines, production debugging.
Evaluation Systems
Eval frameworks that measure what actually matters. LLM-as-a-judge, funnel tracking, A/B pipelines for agent behavior.
0→1 Product Builds
Full-stack AI delivery. I own the surface: backend, infra, LLM layer, deployment. First user to 100K+ users.
> fetching production_deployments... 4 runs found. rendering results.
Run History
> fetching production_deployments... 4 runs found. rendering results.
DRHP Analysis System
First AI system deployed in production at BSE
One of India's first enterprise AI systems adopted inside a major stock exchange. End-to-end agentic RAG for DRHP compliance validation — built for high recall because in compliance, a miss is a failure.
Oolka AI — Multilingual Finance Chatbot
Rebuilt from scratch, scaled 30K → 200K+ MAU
Rebuilt Oolka's entire AI chatbot system from scratch — moved from a brittle single-agent setup to a scalable multi-agent multilingual architecture serving as a personal finance assistant for Indian consumers.
Voice AI Interview Platform
Real-time AI interviewer with dynamic questioning and candidate eval
Built a real-time AI interview platform that conducts live voice interviews — not a static Q&A bot. The system dynamically generates follow-up questions, maintains conversation context, evaluates responses, and outputs structured assessments.
Industrial RL Energy Optimization
~50% energy cost reduction across HVAC, cement plants, airports
Built RL systems using Soft Actor-Critic for real-time industrial energy optimization across HVAC systems, cement plants, and airports. Deployed on Azure Kubernetes with MQTT for real-time sensor data streaming.
Experience
ML Systems Engineer
broken single-agent chatbot, 30K users, no observability
rebuilt multi-agent architecture from scratch, full-stack ownership, scaled infra, A/B eval pipelines, Datadog monitoring
200K+ MAU, scalable multi-agent system, canary deploys live
Founding AI Engineer
compliance team manually reviewing 500+ page DRHP documents
designed and built agentic RAG system, BAML agent framework, hybrid retrieval, structured output enforcement, Kubernetes deployment on AWS
30% → 97% structured parsing success, deployed at BSE production
Research Engineer
manual HVAC and energy controls in industrial environments
built RL systems using Soft Actor-Critic, MQTT real-time data pipeline, Azure Kubernetes deployment across multiple facility types
~50% energy cost reduction across HVAC, cement plants, airports
Research Intern
unstructured visual data requiring automated analysis pipeline
designed computer vision pipeline, model training, evaluation framework, cross-domain generalization research
95% accuracy on benchmark, research pipeline deployed
Tech Stack
How I Work
“Tell me the outcome. I'll figure out the system.”
I've gone zero-to-production on 3 live systems. I don't wait for a spec — I ask what you're trying to achieve and work backwards from there.
“I ship, then improve.”
I've learned where to cut scope and where you absolutely cannot. Every project I've touched is live. Not in staging. Not in a demo. Live.
“I can talk to your CTO and your compliance team.”
I understand architecture tradeoffs and I understand business requirements. I've navigated both in the same week — at a stock exchange.
> all_layers_traversed: true — generating output interface...
Let's build something serious.
currently available for select projects | response_time: < 24 hours