Agentic AI, automations, and the systems behind them.

Multi-agent orchestration, voice agents, and RAG pipelines wired into production.

$10M+
funded startup · core engineer
13+
products shipped
80%
faster legal research
5+ yrs
building web + AI

What I build

services

Agentic AI systems

Multi-agent orchestration in any framework (LangGraph, CrewAI, the OpenAI Agents SDK, or AutoGen), with MCP tooling and LangSmith evaluation.

AI automations

Production workflows in any tool (n8n, Make, Zapier, or GoHighLevel), with approval gates, error handling, and human-in-the-loop.

Voice AI agents

Vapi, Retell, Twilio, and ElevenLabs agents that book, look up records, confirm by SMS, and escalate to a human.

RAG & knowledge systems

Hybrid retrieval that cites its sources and refuses when unsure, over your private docs, data, and APIs.

Full-stack web apps

Next.js and React front ends on FastAPI or Node back ends, from MVP to production, with clean APIs and auth.

Mobile & PWA

Cross-platform mobile apps and installable, offline-capable progressive web apps, built to ship fast.

01

Selected work

7 of 13
01

FrontDesk AI

flagshipcase study →
Solo build, end-to-end2026

Multi-tenant clinic operations platform. A LangGraph multi-agent layer behind a custom MCP server, a Vapi voice agent that books against a live calendar, hybrid RAG (pgvector + full-text + Cohere rerank) that cites its sources and refuses when the docs don't cover a question, and 8 approval-gated n8n workflows.

VapiLangGraphpgvectorCoheren8nFastAPINext.jsSupabaseMCP
02

Strongsuit

case study →
Core AI engineer2024

Legal research and assistant module for litigators. Routes across GPT-4o, Claude, Gemini, Grok and Mistral over FastAPI microservices, with Temporal pipelines, Redis/Arq queues, and CourtListener + SERP integrations.

80% faster research · live monthly paying litigators

LangChainFastAPIPostgreSQLRedis/ArqTemporal
03

Genial

AI engineer, team2025

On the team building Genial's AI agents. I work the agent layer: multi-agent orchestration, MCP tooling, and RAG retrieval, focused on response quality. I evaluate and trace runs in LangSmith, then tighten retrieval and prompting so answers stay accurate and grounded.

LangChainLangSmithMCPRAG
04

PRISM

Solo build2026

A four-stage brand-audit pipeline. One URL in, a full brand strategy with revenue-leak analysis out in about three minutes. Zero human touchpoints.

ClaudeGeminiPython
05

TheHunt

AI integration + UI2024

US estate-sale marketplace. A vision model turns a single photo into item title, description, category, and price estimate. Built the AI layer and the full interface.

VisionGenAINext.jsPWA
06

ClassPilot

Solo build2025

Real-time grading with Gemini Vision: structured JSON streaming, inline error highlighting, teacher overrides, and role-based access.

95% less grading time

Gemini VisionStreamingRBAC
07

Persona AI

Backend + infra2025

Personality SaaS on a 71-function serverless backend. Column-level PII encryption, Big Five scoring (Z-score + cosine similarity), and Chargebee billing.

thousands of users · 98% uptime

AWS LambdaNode.jsChargebee

Also shipped

  • Atomic CRM

    multi-tenant Supabase RLS, per-tenant isolation

  • Mindspo

    18-month CRM automation + AI agent engagement

  • BookOnline

    hotel booking, millions of monthly requests

  • TicketsOnSale

    event ticketing, interactive venue maps

  • Career Counselling Bot

    OpenAI conversational guidance, live

  • DICOM/STL POC

    dental MR navigation, Open3D ICP registration

fig.01

FrontDesk AI / system

how it fits together
Voice
Inbound callVapi agentCalendar checkPatient lookupBook + SMSEscalate to human
Knowledge
Clinic docsHybrid RAG: pgvector + full-text + Cohere rerankCited answeror refuse
Ops
Events8 n8n workflows, approval-gatedLangGraph multi-agentcustom MCP server
Platformmulti-tenant · Supabase · FastAPI · Next.js · citations + refusal enforced end-to-end
proof

What clients say

on video
He's a CTO-level hire.

Founder, Mindspo

After an 18-month engagement: CRM automation, a Next.js build, Stripe, Firebase, and an AI agent.

Have something like this to build?

Start a conversation
02

Stack

what I reach for
Agentic / Orchestration
LangGraphCrewAIMulti-agentLangChainMCPLangSmithOpenAIClaudeGeminiGrok
AI Automations
n8nMake.comZapierGoHighLevelTemporalRedis/ArqWebhooksApproval workflows
Voice
VapiRetellElevenLabsTwilio
Backend
PythonFastAPINode.jsTemporalRedis
Data / Vector
PostgreSQLSupabaseFirestorepgvectorPineconeCohere rerank
Frontend
Next.jsReactTypeScriptTailwindReact NativePWA
Cloud / Infra
AWSAzureFirebaseGoogle CloudDockerVercelStripe
note

About

who you're hiring

I build production agentic AI and automations: multi-agent orchestration, voice agents, RAG pipelines, and the automation workflows that wire them into real products.

I also ship the full stack around them, from web apps to cross-platform mobile and installable PWAs, on Next.js, React, FastAPI, and Node. Core engineer on Strongsuit, a legal-tech platform with live paying users.

I care about systems that ship and hold up, not demos. I work across US and EU time zones.

03

Before we talk

what teams usually ask

Mostly agentic AI and the systems around it: multi-agent workflows, voice agents, RAG over your own docs, and automations that run in production. I build the product too when you need it, web, mobile, or API. I work in whatever stack you already have.

Yes, that's the core of what I do. LangGraph, CrewAI, or whatever your team standardizes on. Tools wired through MCP, runs traced in LangSmith, and human checkpoints when something needs approval before it goes out.

Yes. On FrontDesk AI the voice agent takes inbound calls, checks a live calendar, books, sends an SMS confirmation, logs to the CRM, and transfers when it gets stuck. Same setup works with Vapi, Retell, or Twilio.

Yes. I've shipped eight n8n workflows with approval steps and proper error handling on FrontDesk AI alone. Make and Zapier are the same idea, different triggers. I fit the tool you pay for, not the other way around.

Both. A lot of the time the AI sits inside a normal app: Next.js on the front, FastAPI or Node on the back, mobile if you need it. I don't stop at the model demo.

Yes. Vector search plus keyword search, reranking, inline citations, and it refuses when your docs don't actually cover the question. That pattern is live today on legal research and clinic document Q&A.

Orchestration, tool calls, eval in LangSmith, plus the API and UI around it. Not a chain of prompts in a notebook. I'm a core engineer on a $10M+ funded startup with paying users, so I'm used to shipping, not prototyping.

AWS, Firebase, Supabase, PostgreSQL, Azure when clients require it. On the AI side: LangGraph, CrewAI, Vapi, n8n, and the usual stack. I adapt to what you host on rather than forcing my preferences.

Legal, healthcare, e-commerce, edtech, SaaS, marketing. The moving parts are similar: agents, retrieval, automations. Domain specifics I pick up quickly from your team.

Open to select projects, remote across US and EU time zones (UTC+5). Send a few lines on what you're building through the form below or email hello@rajajahanzaib.dev. I usually reply within a day.

04

Contact

reply within a day

Agents, voice, RAG, or AI automations you need shipped? Or a full-stack partner to build and wire it up? Send a few lines about the problem.

©2026 Raja Jahanzaib. All rights reserved.

Open to select workGet in touch