SENIOR SOFTWARE ENGINEER · AVAILABLE FOR WORK
I build AI-native products end to end: LLM pipelines, voice agents, and full-stack SaaS. Three years in, 10+ shipped, several live with paying users.
Ranchi, India · Remote · overlaps US Eastern
About
I'm a full-stack engineer who owns the whole thing: architecture, LLM orchestration, evaluation loops, telemetry, and the cost-and-latency tradeoffs that keep AI reliable once real users show up. Most of what I've built, I've built solo, top to bottom.
I've worked across medical data, dealership finance, marketing, and developer tooling. I care about correctness. I've paired LLMs with deterministic math engines when the numbers had to be exactly right. And I care about catching failures before users do, with real test coverage instead of hope.
Selected Work
AI revenue optimization for auto dealerships
Heavy financial-data platform on AWS. Parses raw and scanned dealership financial statements, pairs a fine-tuned LLM with a deterministic math engine so numbers are always exact, and lets non-technical stakeholders query in plain English. ~90% plan-to-action time reduction.
Multi-tenant marketing SaaS · 170 active users
AI content, social publishing, email, SEO, landing pages, and lead CRM, all driven by an AI chat command-center, with per-workspace LLM cost metering and Stripe billing. Grew from empty repo to 170 active users.
Published npm SDK · zero runtime deps
7-layer email-deliverability pipeline — syntax, DNS/MX, disposable, role, typo-correction, catch-all, and live SMTP checks — with batch and queue distribution. Cut marketing-email bounce rate by ~95%. Full unit-test coverage on every layer.
Skills & Tools
Writing
Three years, ten products, one person. What actually matters when you build end to end alone, and what doesn't.
Read →The difference between a voice demo and a production voice agent is about 200ms and a barge-in system. Here's what it actually takes.
Read →LLMs in production degrade silently. Here's the eval infrastructure you need before you ship: regression tests, output scoring, and cost monitoring.
Read →Contact
Open to senior full-stack and AI engineering roles, and to interesting contract work. The fastest way to reach me is email.