Available for freelance projects - AI & full-stack roles

Hire me to build AI products.

I'm Kunal - AI Engineer & Full Stack Developer. I help freelance clients and hiring teams turn AI ideas into reliable products: RAG systems, automation workflows, admin panels, APIs, and polished web apps.

Download resume

Hire me for freelance

Hire me full-time

Read blog

AI product systems

Portfolio modeAnime energy, professional delivery.

Available for freelance projectsOpen to AI & full-stack rolesRAG systemsAgentic workflowsMERN + Next.jsAdmin panelsAutomation systemsRemote-ready from IndiaAvailable for freelance projectsOpen to AI & full-stack rolesRAG systemsAgentic workflowsMERN + Next.jsAdmin panelsAutomation systemsRemote-ready from India

Proof in numbers

Signals clients and hiring teams can scan fast.

Work roles

AI + full-stack delivery

Projects shipped

case-study ready builds

200+

DSA problems

algorithmic fundamentals

Certificates

cloud, GenAI, APIs

Scroll-based build path

From brief to shipped product.

For clients, I can scope and build a useful MVP. For companies, I bring AI engineering plus full-stack execution into one practical workflow.

01 / Discovery

Turn messy product ideas into an executable system map.

I start by making the data, users, failure states, and measurable constraints visible before writing code.

02 / Build

Ship the backend, AI pipeline, and interface as one connected product.

RAG, agents, APIs, auth, databases, and UI states are designed together so the experience feels stable end-to-end.

03 / Harden

Instrument the details that separate demos from production.

Latency budgets, fallback flows, prompt boundaries, loading states, and deployment checks make the product easier to trust.

LocationGreater Noida, Uttar Pradesh, India

Primary stackAI - Next.js - MERN

About the engineer

Available for freelance projects and product teams.

AI Engineer and Full Stack Developer specializing in Generative AI, LLM integration, and scalable web applications. Graduated with a B.Tech in Computer Science from Gautam Buddha University, with hands-on experience in building automated agentic pipelines.

Gautam Buddha University

Bachelor of Technology in Computer Science

Aug 2022 - Jun 2026

St. Aerjay Public School

12th, Science

Mar 2020 - Jun 2022

Nirmala Convent School

10th

Mar 2008 - Mar 2020

Work journey

Practical delivery for real teams.

Jul 2026 - Present -

Software Engineer

Technocratiq Digital Pvt. Ltd. - Delhi

Orchestrated 47+ automation workflows across CRM/analytics, architected scalable tracking/reporting systems, and connected multiple business platforms through REST APIs and AI pipelines.

Orchestrated 47+ automation workflows across marketing, CRM, analytics, lead generation, and internal operations, improving efficiency and reducing manual effort.
Architected scalable systems for task tracking, reporting, notifications, and workflow execution, supporting reliable cross-functional operations.
Connected multiple business platforms through REST APIs and AI-driven automation pipelines, enabling seamless data exchange and process automation.

Apr 2026 - Jun 2026 -

AI Intern

Manipal Business Solution - Noida

Automated business workflows and refined conversational AI workflows through prompt optimization and intent validation.

Automated business workflows with Python, APIs, and Google Sheets, cutting manual reporting effort by 90%.
Analyzed operational datasets and developed KPI reports to generate insights for leadership and process optimization.
Refined conversational AI workflows through prompt optimization, intent validation, and response evaluation, increasing answer accuracy by 25%.
Trained task-specific models on labeled datasets, error diagnostics, and performance benchmarking to strengthen output quality.

Jun 2025 - Jul 2025 -

Engineering Intern

Thales Group - Noida

Designed and deployed a Generative AI platform with Google Gemini and OpenAI APIs, embedding LLM capabilities into NLP pipelines.

Designed and deployed a Generative AI platform with Google Gemini and OpenAI APIs, embedding LLM capabilities into enterprise NLP pipelines.
Formulated prompt templates and tuned inference processes to increase LLM output relevance by 30%.
Produced a demo-ready capstone with technical documentation and cross-functional feedback integration.
Conducted data analysis and model fine-tuning with Python and TensorFlow, reducing processing latency by 25% and supporting production-scale deployment.

Feb 2025 - Apr 2025 -

Full Stack Developer Intern

MI Matdar - Maharashtra

Constructed a responsive React.js/Tailwind CSS frontend and built scalable Express.js REST APIs with MongoDB.

Constructed a responsive frontend using React.js and Tailwind CSS, resolving UI/UX bugs and implementing lazy loading to optimize page load times.
Built scalable backend REST APIs with Node.js and Express.js, boosting response time by 40%.
Collaborated in an Agile 7-member team to deploy builds with Vercel and Netlify, maintaining 95% test coverage.
Integrated MongoDB database with schema design and query optimization, handling user records while improving data retrieval efficiency by 35%.

Hire me for

Clear ways I can help you ship.

Pick the path that matches your need: freelance delivery, company role, automation buildout, or a clean production handoff.

View skill architecture

/01

AI product MVPs

Turn an AI idea into a usable product with scoped flows, model integration, auth, admin controls, and polished UX.

RAG systemsLLM appsMVP delivery

/02

Full-time engineering

Join product teams as an AI/full-stack engineer who can ship frontend, backend, database models, and production UI.

Next.jsNode APIsMongoDB

/03

Automation systems

Build workflow tools for lead ops, reporting, reminders, notifications, CRM updates, and repetitive business tasks.

Internal toolsIntegrationsDashboards

/04

Production handoff

Package projects with clean deployment, environment setup, docs, performance checks, and maintainable ownership.

VercelDocsHandoff

Interactive AI sandbox

Inspect the AI behavior before you hire.

Clients can test the AI twin live, adjust model controls, and see how I reason about LLM behavior beyond a polished homepage.

Inference Hyperparameters

System InstructionsDictates the twin's persona, knowledge base, and tone of voice.

Temperature (0.7)Balanced

Max Completion Tokens (250)

Twin Stance Presets

User Query

TERMINAL // INFERENCE_CONSOLE

Console idle. Configure hyperparams, write a query, and hit "Run Inference" to execute.

LATENCY: --

TOKENS: --

MODEL: qwen-3.8-27b

Retrieval walkthrough

Show the pipeline behind the answer.

The RAG walkthrough turns invisible infrastructure into proof: ingestion, chunking, embeddings, retrieval, context injection, and verified output.

1. Document Ingestion

2. Semantic Chunking

3. Embeddings & Storage

4. Vector Retrieval

5. Augmented Generation

Step 1: Raw Document Ingestion

Select a source document to ingest

# raw_text_stream

Thales Group (Engineering Intern, Jun 2025 - Jul 2025, Noida): Designed and deployed an enterprise Generative AI platform using Google Gemini and OpenAI API endpoints. Tuned LLM inference prompts, boosting output relevance by 30% and cutting latency by 25%. Built robust NLP pipelines.

Featured work

Work samples that support hiring decisions.

All projects

Project 01 - 2026

Duli Interiors

Interior Design & Project Management Platform

An end-to-end interior design and project-management platform bringing the entire journey - from AI concept moodboards to 2D floor plans, area-based quotes, and print-ready proposals - into a single collaborative workspace.

latency120ms (Planner)

accuracy99% Area Calc

costReduction45% Estimation Time

Next.jsPythonGoogle GeminiTypeScriptNode.jsTailwind CSS

Case study Live demo Code

Interior Design & Project Management PlatformDuli Interiors

kunal.dev / duli-interiors

Project 02 - 2025

StudyMate

GenAI Powered Study Assistant

A document intelligence application with RAG, semantic search, embeddings, and ChromaDB for contextual PDF summarization and Q&A. Enabled 40% faster document review and reduced review effort by 70%.

latency140ms

costReduction70%

accuracy94.2%

PythonLangChainGroqGradioChromaDBHugging Face

Case study Live demo Code

GenAI Powered Study AssistantStudyMate

kunal.dev / studymate

Project 03 - 2025

AlphaCare

AI-Powered Healthcare Chatbot

Real-time healthcare assistant powered by Gemini, Vapi API, Firebase, and TypeScript for symptom screening and voice interaction. Raised voice-based interaction flow by 45% and user engagement by 35%.

latency280ms (Voice RT)

accuracy96.5% Screening

costReduction35% Support Cost

Next.jsReact.jsNode.jsFirebaseTailwind CSSVapi API

Case study Live demo Code

AI-Powered Healthcare ChatbotAlphaCare

kunal.dev / alphacare

Project 04 - 2025

Notion - Course Selling Application

Secure E-Learning Platform

Secure course-selling platform with role-based dashboards and admin tools. Enabled 50+ instructors to monetize content and reach students in underserved areas, achieving 98% test success across JWT auth flows.

latency65ms (API)

accuracy98.2% JWT Auth Flow

costReduction40% Server Cost

React.jsNode.jsMongoDBExpress.jsTailwind CSS

Case study Live demo Code

Notion - Course Selling Application interface preview

Secure E-Learning PlatformNotion - Course Selling Application

kunal.dev / notion---course-selling-application

Professional signal

Clear reasons to hire.

Case studies

Readable systems

Every featured project is structured around the problem, architecture, constraints, and measurable outcome.

GenAI / RAG

AI with boundaries

LLM features are treated like production surfaces: context windows, fallback paths, retrieval quality, and cost all matter.

UX system

Interface craft

The UI is now editorial, restrained, and content-first while keeping the interactive demos that make the portfolio memorable.

Agent-ready brief

Send this to a recruiter, founder, or hiring bot.

A professional portfolio should work for humans and screening systems. This brief summarizes what I build, where I fit, and how to contact me.

Start conversation

HIRE_KUNAL.md

# HIRE_KUNAL.md

Candidate: Kunal Singh
Role fit: AI Engineer - Full Stack Developer
Location: Greater Noida, Uttar Pradesh, India - remote-ready

Hire for:
- Freelance AI product MVPs
- RAG systems and LLM workflows
- MERN / Next.js web apps
- Admin panels, APIs, dashboards, and automations
- Full-time AI/full-stack engineering roles

Proof points:
- 6+ shipped projects
- 200+ DSA problems solved
- 6+ certificates
- Experience across GenAI, automation, and full-stack delivery

Contact:
- Email: kunalsingh203001@gmail.com
- LinkedIn: https://www.linkedin.com/in/kunal-singh-454368289/

Available for select opportunities

Bring me a real problem.

Hire me for freelance MVPs, AI integrations, automation systems, admin dashboards, or full-time AI/full-stack engineering roles.

Start hiring conversation LinkedIn