Founder lens — Om Jaiswal

01Ownership

Idea → architecture → build → deploy → scale → operate

What Om did at each stage, with the work behind it.

Founding
Backend Engineer at Ravan.AI
Dec 2024 → present. Backend and infrastructure.
3
startups worked with
Ravan.AI, Clinibooth and Medius AI.
2
platforms taken 0 → 1
Proposed, architected and built, not assigned.
4
freelance clients
Delivered solo, working directly with clients.
30+
personal projects
Consensus algorithms, marketplaces, CV research, database internals.
120
people led
Joint Secretary at EduMinerva, across six departments.

01
Idea
Proposing the work before it's assigned.
- Proposed two platforms at Ravan.AI that did not exist yet: a Shopify AI Agent and an internal analytics dashboard.
- 30+ personal projects started from curiosity rather than a brief.
02
Architecture
Deciding the shape of the system, including what's expensive to change later.
- Architected Maya end to end — 7 microservices across Go and Python.
- Designed the tool-routing architecture that keeps 50+ capabilities behind 2 LLM tools.
- Architected Agni's core campaign execution and concurrency-management systems.
- Designed roughly 70% of Clinibooth's backend architecture.
03
Build
Writing it, not handing off a spec.
- Implemented Maya's 7 services personally, not just specified them.
- Delivered 100+ production APIs at Clinibooth across four portals.
- Built 40+ production APIs at Medius AI.
04
Deploy
Getting it into production and owning the path there.
- Migrated production services from Docker-based deployment to MicroK8s.
- Shipped on AWS App Runner, RDS and Secrets Manager at Clinibooth.
- Deployed personal projects on GCP Compute Engine, Cloud SQL and AWS EC2.
05
Scale
Finding the ceiling and moving it.
- Raised outbound calling concurrency from 5 to 300 — a 60× increase.
- Scaled infrastructure to 50K+ AI calls per day.
- Supported 1,000+ concurrent calls with a hybrid scheduler and queue architecture.
06
Operate
Running it in production afterwards.
- Designed and operated a fleet-based LiveKit infrastructure for real-time Voice AI.
- Built geo-routing, manual overrides and self-healing into the fleet.
- Managed LiveKit server capacity dynamically without relying on Kubernetes.

Worked across

Backend
Distributed Systems
AI
Infrastructure
Cloud
Frontend
Product

Not equally deep in all of them — backend and infrastructure are the centre of gravity. The breadth matters because it means fewer handoffs between the idea and the thing running.

02Production systems

Systems in production

Built and run at Ravan.AI — architected, deployed and operated.

01
Maya
AI SecretaryRavan.AI
The problem
Maya has 50+ capabilities. Registering each as its own LLM tool inflates the prompt and degrades tool selection, so the capability set couldn't grow without making the agent worse.
What Om owned
Architected and implemented end to end: 7 microservices across Go, gRPC, Python, FastAPI, Asynq and LangGraph, including the tool-routing layer.
Go
gRPC
Python
FastAPI
Asynq
LangGraph
Deep dive: Routing 50+ capabilities through 2 tools
7
microservices
50+
capabilities
reachable through 2 tools
<500ms
latency
for 80% of requests
02
Agni
Voice AI PlatformRavan.AI
The problem
A live call consumes an LLM slot, a WebRTC session, a telephony channel and infrastructure capacity at once. Each saturates at a different point, so one global concurrency limit either wastes capacity or overruns a layer.
What Om owned
Architected and implemented the core campaign execution and concurrency-management systems, including concurrency controls across every layer.
Python
WebRTC
SIP
RTP
Telephony
Queueing
Schedulers
Deep dive: Four concurrency ceilings, limited independently
1,000+
concurrent calls
4
layers of concurrency control
model · WebRTC · telephony · infra
03
CloserX
Outbound Calling PlatformRavan.AI
The problem
The outbound calling pipeline sustained 5 concurrent calls. The limit came from synchronous execution serialising work that had no ordering requirement, not from hardware capacity.
What Om owned
Architected and scaled the platform, and redesigned the asynchronous calling pipeline end to end.
Django REST Framework
Python
RabbitMQ
Celery
Redis
Deep dive: 5 → 300 concurrent calls
60×
concurrency increase
5 → 300 concurrent calls
50K+
AI calls / day
04
LiveKit Fleet
Real-Time Media InfrastructureRavan.AI
The problem
Real-time voice needs media servers near the user, capacity that tracks demand, and fast removal of failed nodes — without taking on Kubernetes as a dependency.
What Om owned
Designed and operated fleet-based LiveKit infrastructure, including geo-routing, manual overrides, self-healing and dynamic capacity management.
LiveKit
LiveKit Agents
WebRTC
Cloud infrastructure
Deep dive: Running a media fleet without Kubernetes
0
Kubernetes dependency
fleet managed directly
05
Shopify AI Agent & Analytics
0 → 1 PlatformsRavan.AI
The problem
Merchants needed an AI agent inside Shopify, and the team had no internal view of its own data. Both were proposed rather than assigned.
What Om owned
Proposed, architected and built both platforms from 0 → 1. Also migrated production services from Docker-based deployment to MicroK8s.
Python
Docker
MicroK8s
Shopify
OpenAI API
2
platforms from 0 → 1
Docker → MicroK8s
production migration

03Freelance

Freelance

Four clients, scoped and delivered solo, working directly with the client.

Clinibooth
2 contracts · same client5/5
Healthcare platform backend. One client relationship, hired twice for the same body of work.
- Designed and developed roughly 70% of the backend architecture.
- Delivered 100+ production APIs across four portals.
- RBAC via custom permission classes, Stripe payments and MicroBlink ID verification.
- AdvancedMD / AdvancedEMR integration with real-time appointment, provider and medical-record sync.
- Deployed on AWS App Runner with RDS PostgreSQL and Secrets Manager.
- Django REST Framework
- Python
- PostgreSQL
- AWS
- Stripe
- MicroBlink
- Backend Developer Needed for Python Django Project5/5
  Oct 3, 2024 — Oct 8, 2024
FoodieBuddy
Restaurant menu parsing system that turns live restaurant pages into structured menu data.
- Built a FastAPI service to trigger restaurant menu parsing jobs.
- Used Celery for job execution and Playwright for page rendering and extraction.
- Structured the extracted menu data and persisted it.
- FastAPI
- Python
- Celery
- Playwright
- Python Developer Needed for API to Parse Restaurant Menus into JSON4.7/5
  Jun 14, 2025 — Jul 2, 2025
  Client described the work as diligent, professional and flexible, and recommended him.
Travel company
client not named
Backend and page functionality for a travel website.
- Built backend functionality for a travel website using Django and Django Templates.
- Delivered the home and blog page functionality.
- Django
- Django Templates
- Python
- Django Developer Needed for Travel Website Home and Blog Pages5/5
  Oct 18, 2024 — Feb 21, 2025
  Client praised delivery time, dedication and quality.
LeadProKi
Backend work on a lead-scraping platform for a German client.
- Worked on the backend of a lead-scraping platform.
- Built new APIs and shipped backend improvements.
- Extended lead scraping functionality.
- Integrated the OpenAI API.
- Fixed bugs across the existing Django codebase.
- Django
- Django Templates
- Python
- OpenAI API
- Backend Development5/5
  Oct 9, 2024 — Apr 11, 2025

Full contract history on Upwork ↗

04Projects

Projects

30+ built outside work. Systems, full-stack products, and research published in IEEE.

Raft Distributed Consensus Simulation
Distributed systems
A working Raft cluster with a live dashboard showing consensus as it happens.
Why
Built from scratch to understand the algorithm rather than use a library.
Hard part
Implementing leader election, log replication and node failure recovery correctly, then surfacing cluster state in real time without distorting the behaviour being observed.
What Om built
- Full simulation of the Raft consensus algorithm in Go.
- Leader election, log replication and node failure recovery.
- gRPC for peer-to-peer communication between nodes.
- Gin for the HTTP surface and GORM for persistence.
- A Next.js dashboard visualising cluster state transitions and replication events in real time.
A working cluster whose elections, replication and recovery can be watched live.
- Go
- gRPC
- Gin
- GORM
- Next.js
GitHub ↗
Skippit
aka Hyperlocal Freelance AppFull stack
A real-time hyperlocal freelance marketplace — tasks, live location and geospatial matching.
Hard part
Serving geospatial queries and continuous live location updates over WebSockets, without query load growing faster than the user base.
What Om built
- Django and Django REST Framework backend with a React Native (Expo) client.
- Real-time task marketplace built on Django Channels and WebSockets.
- Live location tracking with geospatial queries via PostGIS.
- Redis caching on the hot paths.
- Deployed on a Google Cloud VM.
- Django
- Django REST Framework
- Django Channels
- React Native
- Expo
- WebSockets
- Redis
- PostGIS
- Google Cloud VM
Redis Clone
aka py-redisSystems
A Redis-compatible key-value server in Python — RESP protocol, threaded connections, in-memory store.
Why
Built to understand the protocol and command model from the inside rather than treating Redis as a black box.
Hard part
Parsing RESP correctly and serving concurrent clients over TCP while keeping a small command surface (strings and lists) faithful to Redis semantics.
What Om built
- TCP server on port 6379 with one thread per client connection.
- RESP parser for Redis Serialization Protocol requests.
- Commands: SET, GET, DEL, LPUSH, KEYS, PING.
- In-memory datastore with type checks (e.g. WRONGTYPE on LPUSH against a string key).
- Simple CLI client for interactive use.
A working Redis clone clients can talk to with RESP.
- Python
- TCP sockets
- RESP
- Threading
GitHub ↗
GitHub PR Review MCP
Tooling
A FastMCP server that lets an LLM list, review, comment on and merge GitHub pull requests.
Why
Wire Claude Desktop (and other MCP clients) into a real PR review loop instead of copy-pasting diffs by hand.
Hard part
Exposing GitHub PR operations as MCP tools and prompts so an agent can fetch a diff, suggest review comments, push them, and merge — with auth via a GitHub token.
What Om built
- FastMCP server with tools: list_prs, get_diff, create_pr, review_pr, suggest_comments, push_comments, merge_pr.
- Prompt templates for structured review comments and overall PR review.
- GitHub REST API integration with token auth.
- Claude Desktop config for connecting the server as an MCP tool host.
- Python
- FastMCP
- MCP
- GitHub API
- requests
GitHub ↗
Implementation of Deep Learning in Metro
aka Metro MonitoringResearch
Computer vision system that detects incorrect seat usage in metro carriages and raises alerts automatically.
Why
Reserved-seat compliance is otherwise enforced socially or not at all.
Hard part
No usable dataset existed. The training set was built by hand — 5,000 annotated images.
What Om built
- YOLO-based detection model for seat occupancy.
- A 5,000-image annotated dataset built manually and managed in Roboflow.
- Automated alerting when a seat is used incorrectly.
Provisional patent filed.
- YOLO
- Computer Vision
- Roboflow
- Python
Traffic Prediction using V2X and Clustering
Research
Traffic hotspot detection from V2X vehicle data using unsupervised clustering.
Hard part
Identifying traffic hotspots in V2X / V2AI data without labelled ground truth, which rules out supervised approaches.
What Om built
- K-Means and Agglomerative Clustering applied to the V2X / V2AI dataset.
- Traffic hotspot detection from the resulting clusters.
Published in IEEE — document 10971508.
- Python
- Scikit-learn
- K-Means
- Agglomerative Clustering
IEEE 10971508 ↗
PosterCo
aka E-commerce SystemFull stack
A full-stack e-commerce platform with a recommendation system.
Hard part
Running collaborative-filtering recommendations inside a Django request cycle fast enough to be usable — handled with Scikit-Surprise and Cython.
What Om built
- Django and Django Templates storefront covering product catalog, cart, coupons, order history and payments.
- A lightweight recommendation system built with Scikit-Surprise and Cython.
- Deployed on AWS EC2 with MySQL.
- Django
- Django Templates
- Python
- AWS EC2
- MySQL
- Scikit-Surprise
- Cython
Librosa
aka Library Management SystemFull stack
A production-style library management platform that replaced a paper-based record system.
Why
Replaced a paper system — attendance, seat allocation and student records were kept by hand.
What Om built
- Django REST Framework backend with a React frontend.
- Student tracking, attendance and seat allocation.
- Digital records replacing the paper-based system.
- Deployed on GCP Compute Engine with Cloud SQL.
- Django REST Framework
- React
- Python
- GCP Compute Engine
- Cloud SQL
Command Store
Tooling
A Next.js SPA for saving, searching and organising CLI commands — local-first, with import/export.
Why
A personal vault for commands that are easy to forget and annoying to dig out of shell history.
Hard part
Keeping it useful as a daily tool: fast search, tag filters, one-click copy, and JSON backup without a backend.
What Om built
- Next.js + React SPA with localStorage persistence.
- Search and tag filters across saved commands.
- Add / edit / delete with one-click copy to clipboard.
- Import and export commands as JSON.
- Next.js
- React
- TypeScript
- Tailwind CSS
- localStorage
GitHub ↗

05Experience

Experience

- Architected and implemented Maya, an AI Secretary, end to end: 7 microservices across Go, gRPC, Python, FastAPI, Asynq and LangGraph.
- Designed a novel tool-routing architecture that lets the LLM reach 50+ functions through just 2 tools.
- Architected and implemented the core campaign execution and concurrency-management systems for Agni, Ravan.AI's advanced Voice AI platform.
- Supported 1,000+ concurrent calls using a hybrid scheduler and queue architecture.
- Designed concurrency controls spanning the model, WebRTC, telephony and infrastructure layers.
- Worked extensively with SIP, RTP, telephony and PBX systems in the Voice AI call path.
- Architected and scaled CloserX using Django REST Framework, Python, RabbitMQ and Celery.
- Redesigned the asynchronous calling pipeline, increasing outbound concurrency from 5 to 300 — a 60× increase — using distributed task processing, priority-based queuing and optimised call orchestration.
- Scaled infrastructure to support 50K+ AI calls per day.
- Designed and operated fleet-based LiveKit infrastructure for real-time Voice AI, with geo-routing, manual overrides and self-healing.
- Managed LiveKit server capacity dynamically without relying on Kubernetes.
- Proposed, architected and built two platforms from 0 → 1: a Shopify AI Agent and an internal analytics dashboard.
- Migrated production services from Docker-based deployment to MicroK8s.
- Go
- Python
- gRPC
- FastAPI
- Django REST Framework
- Asynq
- LangGraph
- RabbitMQ
- Celery
- Redis
- LiveKit
- LiveKit Agents
- WebRTC
- SIP
- RTP
- PBX
- Telephony
- Docker
- MicroK8s
- Designed and developed roughly 70% of the backend architecture.
- Delivered 100+ production APIs across four portals using Django REST Framework.
- Implemented RBAC through custom permission classes.
- Integrated AdvancedMD / AdvancedEMR with real-time synchronisation of appointments, providers and medical records.
- Integrated Stripe for payments and MicroBlink for ID verification.
- Ran the platform on AWS App Runner, RDS PostgreSQL and Secrets Manager.
- Worked directly on healthcare workflows and their compliance-sensitive edge cases.
- Django REST Framework
- Python
- PostgreSQL
- AWS App Runner
- AWS RDS
- AWS Secrets Manager
- Stripe
- MicroBlink
- AdvancedMD / AdvancedEMR
- Built 40+ production APIs using Django REST Framework.
- Offloaded heavy workloads to Celery and Redis, including automated email jobs and other background processing.
- Optimised PostgreSQL, and wrote raw SQL for data seeding and migrations.
- Built CSV ingestion and data processing pipelines.
- Implemented JWT authentication with token rotation, plus CORS and general security best practices.
- Collaborated with a cybersecurity consultant on hardening.
- Django REST Framework
- Python
- Celery
- Redis
- PostgreSQL
- Raw SQL
- JWT
- Developed Python applications for client-facing workflows.
- Built a Python application that fetched 1M+ Zendesk tickets into SQL databases, supporting brand-level querying.
- Automated Amazon Video Central sales-report downloads with configurable date ranges, frequencies and territories.
- Automated YouTube analytics and sales reporting.
- Worked extensively with OAuth 2.0 and scheduled reporting jobs.
- Python
- SQL
- OAuth 2.0
- Zendesk API
- Amazon Video Central API
- Apple iTunes API
- YouTube Reporting API
- YouTube Analytics API

06Leadership

Leadership

Student leadership at BVCOE — teams, departments and events.

EduMinerva
Joint Secretary
Jun 2023 — Jun 2024
120
people led
6
departments overseen
8
events curated
300+ attendees each
- Led a team of 120 people across six departments.
- Worked directly with the President and Vice-Presidents, acting as the bridge between the Core Team and executives.
- Planned and curated eight technical and non-technical events, regularly drawing 300+ attendees.
- Responsible for overall functioning and cross-department coordination.
- Guided and trained freshers.
EduMinerva
Event Management Head
Jun 2022 — Jun 2023
10
executives led
- Led a team of 10 Event Management Executives.
- Planned and executed events alongside the Core Team.
- Provided logistical support across departments.
Alumni Cell BVCOE
Head — Food and Beverages Team
Jan 2024 — May 2024
~700
people catered for
500 alumni · 200 staff
- Led a team of 6.
- Managed food requirements for an alumni event.
- Coordinated catering for approximately 500 alumni and 200 staff.

07Contact

Contact

Open to conversations about backend and infrastructure work.

work.omjaiswal@gmail.com Resume LinkedIn ↗GitHub ↗Upwork ↗

New Delhi, India · Press L to switch lenses.

Idea → architecture → build → deploy → scale → operate

Idea

Architecture

Build

Deploy

Scale

Operate

Systems in production

Maya

Agni

CloserX

LiveKit Fleet

Shopify AI Agent & Analytics

Freelance

Clinibooth

FoodieBuddy

Travel company

LeadProKi

Projects

Raft Distributed Consensus Simulation

Skippit

Redis Clone

GitHub PR Review MCP

Implementation of Deep Learning in Metro

Traffic Prediction using V2X and Clustering

PosterCo

Librosa

Command Store

Experience

Ravan.AI

Clinibooth Inc.

Medius AI

KDataScience Solutions

Leadership

Joint Secretary

Event Management Head

Head — Food and Beverages Team