I design systems
that stay up.
Designer → AI Systems Engineer
Founding engineer at Zencia.ai. Real-time voice agents, RAG pipelines, and privacy-first AI that runs on your own hardware — architected, built, and deployed solo. Not demos. Production.
- 50 concurrent sessions
- 90+ languages
- Cloud or on-premise
Hover a stage to inspect it
Running in production
right now
Three products, each built and deployed solo. Click through — they're all reachable.
Zencia SaaS Platform
Multi-tenant AI platform across 22 API modules — owner accounts, client portals, agent builder, per-agent knowledge bases, billing with plan tiers, partner API, and an embeddable widget.
Zencia Echo
Realtime speech-to-speech voice agent in 90+ languages, with barge-in, persistent per-caller memory, and 50 concurrent sessions on an async registry. Three telephony providers behind one interface.
BuiltBy — Developer Social Platform
A social platform where the post is the product. Builders upload a bundle or import a GitHub repo and it runs live in a sandboxed player inside the feed — no deploy step. Verified-only posting, usage-derived Build Score, jobs board, DMs.
I started with pixels.
Now I build systems.
Self-taught engineer in Lucknow. I came up through graphic design, so I care how a system looks from the outside as much as how it holds together inside.
Founding engineer at Zencia.ai, specialising in privacy-first, on-premise AI: local inference, local TTS, zero cloud dependencies.
Alongside that I build and run BuiltBy — a developer social platform where uploaded code runs live in the feed. Next.js and Firebase, solo, from the execution sandbox to the Android build.
- Current
- Founding engineer, Zencia.ai
- Discipline
- Voice AI · RAG · on-prem LLM · infra
- Primary stack
- Python · FastAPI · asyncio · React
- Domains
- Automotive · Healthcare · Enterprise SaaS
- Deployment
- Cloud, or fully on-premise with no cloud calls
- Mode
- Solo build, architecture to deploy
- Status
- Open to work
Where I've built
Lucknow, IN
AI Systems Engineer
Zencia.ai / Sole developer — frontend to backend
- Sole architect of a live multi-tenant AI SaaS platform — 17-module Flask Blueprint codebase covering agents, knowledge bases, call logs, billing, phone numbers, SMS, calendar, client portal, partner API and admin.
- Built a production voice agent in 90+ languages: FastAPI + asyncio WebSocket server, bidirectional PCM streaming, barge-in handling, and an async session registry capped at 50 concurrent sessions.
- Shipped an AI demo platform to GCP solo — Nginx reverse proxy, Let's Encrypt SSL, systemd, React/Vite frontend.
- Designed and presented a complete AI voice platform to Hyundai — inbound/outbound calling, lead scoring, test-drive booking, CRM integration.
Lucknow, IN
Tech Executive
Zotomation Pvt Ltd
- Developed and maintained 5+ client websites — Python backends with HTML/CSS/JS frontends.
- Built business automation workflows that cut manual processing time for clients.
- Supported development of AI-powered customer service solutions.
BBD University
BCA, Computer Applications
Babu Banarasi Das University / 83%
- Data structures, algorithms, DBMS, software engineering, computer networks.
What I build with
Not a wishlist — everything below is in something I've shipped.
The whole stack runs
on your hardware
For teams whose data is not allowed to leave the building. Every layer below has a local path — not a cloud service with a privacy policy attached.
Local inference
Open-weight models served on the customer’s own machine, swappable at runtime. Retrieval-augmented answers are generated in place.
No prompt leaves the networkLocal speech
Transcription and synthesis both run on CPU — a sub-4M-parameter open-weight voice model through ONNX Runtime, with voice-activity detection for hands-free turns.
No audio leaves the deviceLocal retrieval
Documents are chunked, embedded and indexed into a vector store on the same machine, with background re-indexing as the corpus changes.
No document leaves the diskPackaging Shipped as a desktop application where required — no browser install, no account, no outbound connection.
Built for founders who
need it to actually run
Production AI — voice agents, LLM pipelines, full-stack platforms. Architecture through deployment. All projects ↗
AOLOA Saarthi — Smart Glasses for Blind Users
Bluetooth smart glasses that let blind and low-vision users ask what is in front of them and get a spoken answer. The hardware shi…
Local Voice AI on CPU
A hands-free voice assistant whose speech stack runs entirely on a CPU — no cloud speech service, no GPU required. Microphone, voi…
AI Voice Agent with Memory
A production voice agent that answers and places real phone calls in 90+ languages, remembers who it is talking to, and acts on wh…
BuiltBy — Developer Social Platform
A social platform for developers where the post is the product. Instead of a screenshot or a recorded demo, builders upload a bund…
Realtime Talking Avatar
A photoreal talking head that holds a spoken conversation — voice in, lip-synced video out, generated live on a GPU rather than pr…
MedTalks — Medical English Platform
An English-language training platform for doctors, nurses, pharmacists and dentists, built around AI voice agents that let student…
The front end of the system
Sites and interfaces designed and built from scratch — the design half of the discipline.
Notes from the build
All entries ↗
From Hype to Reality: What It Takes to Build Enterprise AI System
Most AI products look great in a demo. Building systems that actually work inside a company is a different problem entirely — and most teams underestimate it.
Building AI That Actually Works: Lessons from Real-World Deployments
Deploying AI in a real business environment is a fundamentally different problem from building a demo. Seven lessons from the field on what it actually takes to make AI work in production.
The Gap Between AI Demos and Production Systems
Every AI demo looks impressive. Production is where the real test begins — and where most systems quietly fall apart.
Got a system
that needs building?
Tell me the constraint you're stuck on. I'll tell you whether I can solve it — and roughly what it takes.