AI Lab · 4 live demos

I build intelligent systems, AI-powered products, and experiences that turn complex technology into useful software.

Hire meView Projects
02Experience

Built in production. Led end to end.

Two roles, one trajectory — from full-stack products under real traffic to leading AI products from idea to release.

Current role — AI products end to end
Project lead
Daily API transactions served
5,000+
p95 API response time
<200ms
Best Employee of the Year
2026

  1. Owning AI products from the first requirement to the production release.

    I lead AI product delivery end to end — shaping requirements, designing the architecture, coordinating the team and taking releases live. The work sits where LLMs meet real operations: automations that replace manual workflows, backends that stream model output, and mobile apps with AI built in.

    Key contributions05
    1. 01

      Project lead, idea to production

      Own delivery of AI products end to end — requirements, architecture, team coordination and the production release.

    2. 02

      Replaced manual client workflows with n8n + LLM pipelines

      Custom automations that removed repetitive operations across notifications, reminders, planning and task management.

      • n8n
      • LLMs
    3. 03

      Node.js and Python backends that stream LLM output

      Scalable REST APIs over PostgreSQL, with LLM streaming and prompt orchestration built into the request path.

      • Node.js
      • Python
      • PostgreSQL
      • REST APIs
    4. 04

      Flutter apps with AI built in

      Mobile apps with chat, voice and document Q&A, connected to the backend services.

      • Flutter
      • LLMs
    5. 05

      Zero-downtime releases on AWS

      Production systems deployed and run on AWS, shipped through CI/CD pipelines.

      • AWS
      • CI/CD
    Stack
    • LLMs
    • n8n
    • Node.js
    • Python
    • Flutter
    • PostgreSQL
    • AWS
    • CI/CD
  2. Dec 2025 · Moved into AIFull Stack DeveloperAI Developer · Project LeadFrom shipping web products at scale to owning AI products end to end.

  3. Building production web products — and the APIs that carry their traffic.

    I joined in my final year of college and worked across the whole stack, from Next.js interfaces to Node.js services. It's where production became real: steady traffic, strict latency budgets and releases that couldn't break.

    Key contributions03
    1. 01

      AI-driven web applications on MERN + Next.js

      Platforms that automated internal workflows and improved delivery turnaround.

      • MongoDB
      • Express
      • React
      • Node.js
      • Next.js
    2. 02

      REST APIs under real traffic

      Node.js and Express services handling 5,000+ daily transactions at sub-200ms p95 response times.

      • Node.js
      • Express
      • SQL
    3. 03

      A containerized release path

      Services packaged with Docker and shipped through CI/CD to AWS, making releases more reliable.

      • Docker
      • CI/CD
      • AWS
    Stack
    • Next.js
    • React
    • Node.js
    • Express
    • MongoDB
    • SQL
    • Docker
    • AWS
03Projects

Selected work.

AI systems I've designed end to end, and production products from client work. Open any project to see the problem, the architecture, and how it was built.

Next.jsTypeScriptLangChainLangGraphOpenAI
01Project2026

Agentic AI repository analyzer — a multi-agent system for codebase understanding.

  • Multi-agent orchestration
  • RAG over source code
  • Real-time agent progress
View case study
React.jsNode.jsGoogle Gemini APIWeb Speech APIMongoDB
02Project2025

A voice-first assistant with LLM intent classification and a low-latency speech pipeline.

  • LLM intent classification
  • Speech-to-text + text-to-speech
  • Pluggable command handlers
View case study
n8nLLMsNode.jsPythonPostgreSQL
03Professional work2025 — now

n8n + LLM pipelines and AI-enabled apps delivered as project lead at Freedom With AI.

  • Replaced manual client workflows end-to-end
  • LLM streaming + prompt orchestration
  • Zero-downtime releases on AWS
View case study
Next.js 16TypeScriptTailwind CSS v4Canvas 2DRoute Handlers
04This site2026

The portfolio you're using — a grounded assistant, a live retrieval engine, and an evaluator.

  • In-browser vector search
  • Grounded, streamed answers
  • Four live AI experiments
View case study
03.BClient work

Products in production.

Live products used every day — wellness, AI coaching, customer chat, AI agents, computer vision, marketplaces, and restaurant operations.

Live product
Next.jsTailwind CSSRazorpay
Wellness platform · Live product

A bilingual holistic-wellness platform with its own admin console — memberships, live webinars, appointments, a natural-products store and patient nutrition plans.

View case study
Live product
Next.jsVercel
EdTech · AI-native coaching school

India's AI-native coaching business school — an AI Sprint builds a coaching plan with each student, in English, Hindi or Marathi.

View case study
Live product
ChatwootVue.jsVite
Customer chatbot · Live product

The customer chatbot inside Freedom With AI's products — a chat widget on every page, with a team inbox behind it.

View case study
Next.jsTypeScriptAI/LLM
AI SaaS · Creator analytics

Pre-publish AI scoring that flags a weak hook, title, or thumbnail before a video goes live.

View case study
Live product
Next.jsAI AgentsTypeScript
AI SaaS · Autonomous sales agents

Five role-based AI agents that keep a revenue pipeline moving outside working hours.

View case study
Live product
Next.jsAI/LLMTypeScript
AI SaaS · Website chatbot

A self-training chatbot that learns a website on its own and goes live from a one-line embed.

View case study
Next.jsTypeScriptGoogle MediaPipe
Computer vision · Wellness

In-browser face, hand, and pose tracking that turns a webcam into live posture and attention scores.

View case study
Next.jsReactMongoDB
PropTech · Property marketplace

A map-first marketplace for verified plots, homes, and commercial listings with direct owner contact.

View case study
Next.jsNode.jsRazorpay
Restaurant management platform

Ordering, billing, reservations, and delivery-platform orders unified in one restaurant system.

View case study
04Skills · How I build

How I build

Not a list of logos — a system. Each layer calls the one below it. Select a component to see where it runs in real work.

L1 · 5 parts
Interface
Where people meet the system
L2 · 6 parts
Intelligence
Models, retrieval, and reasoning
L2 · Intelligence

RAG

Retrieval pipelines that ground model answers in source data — e.g. code embeddings in Pinecone.

Where it's used
  • RepoMind
  • This site
L3 · 5 parts
Services
APIs, streaming, orchestration
L4 · 4 parts
Data
State, memory, and storage
L5 · 4 parts
Infrastructure
Shipping reliably
Full toolkit43 tools · and counting
  • OpenAI
  • Anthropic Claude
  • Google Gemini
  • LangChain
  • LangGraph
  • RAG
  • AI Agents
  • n8n
  • Pinecone
  • ChromaDB
  • pgvector
  • OpenAI Embeddings
  • Semantic Search
  • TypeScript
  • JavaScript
  • Python
  • Java
  • C++
  • SQL
  • React.js
  • Next.js
  • Tailwind CSS
  • Flutter
  • HTML
  • CSS
  • Node.js
  • Express.js
  • FastAPI
  • REST APIs
  • WebSockets
  • SSE
  • JWT
  • PostgreSQL
  • MongoDB
  • MySQL
  • Redis
  • SQLite
  • AWSEC2 · S3 · Lambda · RDS · Bedrock
  • Vercel
  • Docker
  • CI/CD
  • Git
  • GitHub

Pick a group to light it up

Yusuf Hussain at his desk, reading code on his monitor
Yusuf Hussain
AI Full-Stack Engineer
Project lead · Freedom With AI
Best Employee 2026
05About

AI engineer by craft. Full-stack by habit.

I'm Yusuf — an AI full-stack engineer. I build LLM products end to end: retrieval, agents, and automation, the APIs and data behind them, and the interfaces people actually use.

I studied Computer Science at a tier-3 college in Patna — no placement pipeline, no financial cushion — so I taught myself what the syllabus didn't. I was hired as a Full Stack Developer in my final year, moved into AI full-time at Freedom With AI as a project lead, and was named Best Employee of the Year 2026.

CGPA
8.5 / 10
Daily transactions
5,000+
DSA problems
100+
Hire me LinkedIn
Freedom With AI trophy engraved with Yusuf Hussain's name 2026
RecognitionFreedom With AI

Best Employee of the Year 2026.

Recognized for treating client problems as his own — including the ones that broke at 2 AM — and for growing into responsibility as a project lead.

“Ownership can't be assigned.”
Read the LinkedIn post
Journey2021 — now

A tier-3 college, a laptop, and a habit of shipping

No big-name campus. No placement pipeline. No financial cushion. Just consistency — and the belief that skills compound faster than circumstances.

  1. 2021 · Patna
    Tier-3 college, first-tier ambition

    Yusuf started B.Tech in Computer Science at R.P. Sharma Institute of Technology, Patna — a tier-3 college with no big-tech placement pipeline. He finished as one of its standout students, with a CGPA of 8.5.

  2. 2021 — 2024
    Learning what the syllabus didn't teach

    With money tight, the internet became the classroom: 100+ LeetCode problems, certifications in DSA with Java and C++, a hackathon build, and a lot of late nights.

  3. Aug 2024
    Hired before graduating

    While still in his final year, he joined as a Full Stack Developer — shipping MERN + Next.js apps and REST APIs handling 5,000+ daily transactions at sub-200ms p95.

  4. Dec 2025
    Into an AI company

    He moved into AI full-time at Freedom With AI — leading AI product delivery end-to-end, building n8n + LLM automation pipelines, Flutter AI apps, and AWS deployments.

  5. 2026
    Best Employee of the Year

    Within a year of joining, Freedom With AI named him Best Employee of the Year 2026. In his words: a milestone, not a destination.

Education
Sept 2021 — May 2025
B.Tech in Computer Science and Engineering
R.P. Sharma Institute of Technology, Patna
CGPA
8.5 / 10
Certifications & practice
  • 100+ DSA problems solvedLeetCode
  • Alpha — Data Structures & Algorithms with JavaCourse certificate
  • C++ Foundation ProgramPhysics Wallah · Certificate
  • Inter-college hackathonBuilt a collaborative web-based solution
06Ask Yusuf

Ask Yusuf

Ask anything about my experience, projects, skills, and engineering work.

yusuf.assistant

What would you like to know?

Answers are retrieved from the knowledge base built from Yusuf's real experience — no invented facts.

Answers use portfolio data only
07AI Lab

The AI Lab.
Systems you can inspect.

Four live experiments that show how the systems behind AI products actually work — retrieval, orchestration, perception, and evaluation. Nothing here is a video.

Stage 04 / 08Not run

Vector search

Converts the query into an embedding and retrieves the most relevant knowledge from the vector store — cosine similarity against every chunk.

33
chunks indexed
256
vector dims
5
top-k

Run a query to trace it through the pipeline. Every number you'll see — terms, vector components, similarity scores, token counts — is computed live from the portfolio's knowledge base.

08Contact
Available for AI engineering roles

Let's build something intelligent.

I'm interested in building useful products at the intersection of software engineering and AI.

Hire me Ask my AI first
Direct lineEmail · WhatsApp · LinkedIn
Email
yusuf.aman00@gmail.com