WALEED.
MUHAMMAD WALEEDFULL STACK DEVELOPER & AI ENGINEER

Engineering Intelligent Software for Real-World Business Problems.

INDEX // 01
01

I build custom web applications, AI-powered knowledge systems, and intelligent workflow automations that help businesses simplify complex operations.

Engineered for B2B companies, SaaS startups, and training providers—combining type-safe Next.js & PostgreSQL architecture with citation-backed RAG assistants and human-in-the-loop n8n workflows.

CORE ENGINEERING CAPABILITIESVIEW SERVICES →
Custom Web & SaaS AppsNext.js & TypeScriptPostgreSQL (pgvector)RAG Knowledge SystemsAI Document Processingn8n Workflow AutomationRedis & WebSocketsAWS & Docker
FIG. 01 // ENGINEER PROFILEWALEED KN
Muhammad Waleed (Waleed KN) — Full Stack Developer & AI Engineer
FOCUSFull-Stack, RAG & Automation
STACKNext.js • TypeScript • Postgres
BASEPeshawar, PK (Remote Global)
SECTION 02/ Production Portfolio

SELECTED
WORK.

Experiments, products, and engineering projects.

All Projects (10)
FEATURED CASE STUDY // 01AI / MLIndependent Engineering Project
YEAR // 2026
PLATE 01RAG Document Q&A — AI Assistant with Cited Answers
[ SYSTEM PREVIEW // 01 ]PRODUCTION BUILD
PGVECTOR INDEXGEMINI EMBED
CHUNK #14 (P. 04)0.89 SIM
CHUNK #22 (P. 09)0.84 SIM
THRESHOLD GUARDACTIVE
CITED SYNTHESIS // GROQCI + 30+ TESTS

Verified answer synthesized from uploaded PDF context with strict page-level source attribution and automatic model fallback.

[CITATION: PAGE 04][CITATION: PAGE 09]
VERIFIED ARCHITECTUREWALEED // 01
ENGINEERING HIGHLIGHTS
  • 01Built and deployed a document Q&A app that returns page-level cited answers and declines out-of-scope questions, through semantic search with a similarity threshold, using pgvector, Gemini embeddings, and Groq at $0 infrastructure cost
  • 02Kept the app reliable within free-tier API limits through resumable batch embedding, automatic model fallback, and Postgres-backed rate limiting (3 questions per minute per visitor), using Next.js route handlers and Neon
  • 03Shipped with 30+ unit tests, an evaluation harness that scores answer correctness, citation accuracy, and refusals, and CI on GitHub Actions (lint, type-check, tests, build, Docker image)
01PRIMARY CASE STUDY

RAG Document Q&A — AI Assistant with Cited Answers

Page-level cited document Q&A with semantic search, similarity thresholding, and $0 infrastructure cost.

Built and deployed a document Q&A app that returns page-level cited answers and declines out-of-scope questions through semantic search with a similarity threshold, using pgvector, Gemini embeddings, and Groq at $0 infrastructure cost.

PROBLEM & TARGET USERS

Standard LLM chat interfaces hallucinate answers when queried against private PDFs and fail to tell users which exact page a claim came from or when a question falls outside the uploaded documents.

Users: Training teams, researchers, analysts, and internal operations staff who need verifiable, page-cited answers from technical manuals and PDFs.

TECHNOLOGY STACK
Next.jsTypeScriptPostgreSQL (pgvector)GeminiGroqDockerGitHub Actions
CASE STUDY 02/ AI / ML
Independent Engineering Project
PLATE 02MCQForge — Automated Document-to-MCQ Assessment Platform
[ SYSTEM PREVIEW // 02 ]PRODUCTION BUILD
PDF.JS + MAMMOTH + OCR
Multi-Column MCQ & Key Extractor
CONFIDENCE + DEDUP
UPSTASH REDIS LUA113+ VITEST + E2E
Session-Isolated Review & Timed Exam Engine
STRICT ZOD SCHEMA VALIDATION
VERIFIED ARCHITECTUREWALEED // 02

MCQForge — Automated Document-to-MCQ Assessment Platform

Full-stack assessment platform extracting MCQs and answer keys from multi-column PDF, DOCX, and TXT study documents.

Engineered a full-stack assessment platform that extracts multiple-choice questions and answer keys from multi-column PDF, DOCX, and TXT study documents with OCR fallback, confidence scoring, and duplicate detection. Built session-isolated question review and timed/untimed exam workflows backed by Upstash Redis atomic Lua scripts, strict Zod schema validation, 113+ Vitest unit tests, and Playwright E2E tests.

Next.jsTypeScriptUpstash Redis (Lua)PDF.jsMammothZodVitestPlaywright
CASE STUDY 03/ Full-Stack
Independent Engineering Project
PLATE 03RideShare — Real-Time Ride-Hailing Platform
[ SYSTEM PREVIEW // 03 ]PRODUCTION BUILD
REDIS GEOSPATIAL + WEBSOCKETLIVE STATE MACHINE
REQUESTED→ACCEPTED→IN PROGRESS→PAID
VERIFIED ARCHITECTUREWALEED // 03

RideShare — Real-Time Ride-Hailing Platform

Real-time rider-driver matching via Redis geospatial index, WebSockets, and a 5-state ride lifecycle.

Built real-time rider-driver matching through a Redis geospatial index and WebSocket live location and ride-status updates in a full-stack Next.js platform with a server-validated 5-state ride lifecycle.

Next.jsWebSocketRedis (geospatial)MapboxStripe (test mode)JWT
CASE STUDY 04Portfolio Demonstration
AI Cold Email Automation n8n workflow: Google Sheets leads, Groq research, AI agent drafting and quality check

AI Cold Email Automation (n8n)

Two human-in-the-loop n8n workflows that research company websites with Groq, draft quality-checked cold emails, and dispatch approved sends.

  • —Human approval before any email is sent
  • —Duplicate and unsubscribe protection
  • —Fail-safe pause switch
n8nGroq (openai/gpt-oss-20b)Google SheetsGmailJavaScript
CASE STUDY 05Independent Engineering Project
CODESCOUT RAGPGVECTOR · 768D
01 Ingest02 Index03 Cite

CodeScout — AI Codebase Intelligence & RAG

Index any public GitHub repository into Neon pgvector and ask plain-English questions backed by exact file and line-range citations.

  • —Streaming in-memory GitHub tarball ingestion skipping lockfiles, binaries, and node_modules
  • —40-line overlapping vector chunks with 1-based line numbers in Neon pgvector (768-D)
  • —Zero-hallucination answers with clickable path:start-end citations and strict refusal guardrails
Next.jsTypeScriptNeon (pgvector)RAGGitHub API
OPEN SOURCE // ARCHIVE8+ REPOS

EXPLORE MORE ON GITHUB.

Inspect additional deployed systems including E-Commerce Platform, Retail POS System, Movie Search App, and Recipe Finder.

E-Commerce PlatformAuth.js + Prisma
Retail POS SystemPrisma + PG
Movie Search AppTMDB API
Recipe FinderSpoonacular
GitHub Profile FinderGitHub API
github.com/waleed-kn
SECTION 03/ EdTech & Training Systems

LEARNING & TRAINING
SOLUTIONS.

Custom AI assistants, assessment automation, and learning portals I design and build for training providers, academies, and education businesses.

CAPABILITY OFFERINGBuilt for professional training providers, certification academies, corporate L&D teams, and EdTech companies.
CUSTOM ARCHITECTED TO ORDER
SOLUTION 01

AI Learning Assistant

Grounded Q&A and instant search across your proprietary course materials.

A custom RAG-powered learning assistant indexed directly on your curriculum documents. Students ask natural-language questions and receive context-aware explanations with exact page or module citations—and clear refusals for out-of-syllabus queries.

  • —Semantic search across course PDFs, handbooks, and study guides
  • —Context-aware Q&A tailored to training materials
  • —Page-level & module-level source citations for verification
  • —Out-of-scope refusal guards to prevent off-curriculum hallucinations
SOLUTION 02

Assessment Automation

Automated extraction, structuring, and delivery of practice & certification exams.

An automated document-to-assessment pipeline that parses PDF, DOCX, and TXT question banks (with OCR fallback for scans), scores extraction confidence, flags duplicates, and feeds timed or untimed exam interfaces.

  • —Document-based MCQ & answer-key extraction (PDF, DOCX, TXT)
  • —Confidence scoring & duplicate question detection
  • —Review queue for instructors before publishing assessments
  • —Session-isolated timed & untimed student exam interfaces
SOLUTION 03

Learning Management Systems

Custom portals for cohorts, course delivery, progress tracking, and administration.

A tailored full-stack learning portal built around your exact training workflow—connecting student dashboards, course modules, automated assessments, and administrative reporting in one owned codebase.

  • —Clean student dashboards for active courses, exams & results
  • —Structured course & module content management
  • —Cohort progress tracking & assessment score history
  • —Integrated assessment management & grading workflows
  • —Role-based administrative workflows & reporting exports
SECTION 04/ About Me

THE ENGINEER
BEHIND THE CODE.

Full-stack product engineering, backend systems architecture, and applied agentic AI.

PROFILE DOSSIER

MUHAMMAD WALEED

Muhammad Waleed (Waleed KN) — Full Stack & AI Engineer in Peshawar, Pakistan

“SYSTEMS SHOULD BE FAST, TYPE-SAFE, AND BUILT TO SOLVE CONCRETE PROBLEMS.”

Peshawar, PakistanCUSIT SE // 2024–2028
01 // PROFESSIONAL SUMMARYFULL STACK & AI ENGINEER

Full Stack and AI Engineer (Next.js, TypeScript, PostgreSQL) with 8+ deployed applications, including a cited-answer RAG app on a $0 stack and a real-time ride-hailing platform.

Pursuing a B.S. in Software Engineering at CUSIT, Peshawar (2024–2028). Completed 4 certifications in AI agents, RAG, MCP, n8n automation, and AWS Fundamentals alongside client web development as a Software Development Intern at Crixsoft.

02 // ENGINEERING RIGOR

Production-Grade Reliability.

From 30+ unit tests with Vitest, evaluation harnesses, and GitHub Actions CI/Docker pipelines to server-validated 5-state machines and Zod schema guards, I engineer systems for real-world reliability.

VITEST • DOCKER • GITHUB ACTIONS CI
03 // VERIFIED CREDENTIALS

4 Cloud & AI Certifications.

Certified in AI Automation Engineer with n8n (7 courses), AWS Fundamentals (3 courses: EC2, S3, IAM, VPC, Lambda), Build Production AI Agents with RAG & MCP, and Agentic AI Foundations.

RAG • MCP • N8N • AWS CLOUD
04 // CAREER DIRECTIONOPEN TO JUNIOR DEV ROLES

Seeking a junior developer role on a growing engineering team where I can contribute to full-stack Next.js/TypeScript products, relational database architectures, and production AI systems.

Full-stack engineeringBackend architectureAI engineeringAgentic AI systemsCloud computingBuilding real-world products
View Full Resume / CVREMOTE & ON-SITE READY
SECTION 05/ Technical Expertise

MY
TOOLKIT.

Verified technologies and cloud primitives used across deployed full-stack and AI applications.

DOMAIN 01/ CORE PROGRAMMING & QUERYING
5 TECH

LANGUAGES

Writing strict, type-safe application logic, relational SQL queries, and semantic web markup.

TypeScriptJavaScriptSQLHTMLCSS
DOMAIN 02/ FULL-STACK & TESTING RUNTIME
9 TECH

FRAMEWORKS & TOOLS

Building full-stack web platforms, REST APIs, authentication flows, schema validation, and unit test suites.

Next.jsReact.jsNode.jsExpress.jsTailwind CSSPrisma ORMAuth.jsZodVitest
DOMAIN 03/ RELATIONAL, VECTOR & GEOSPATIAL
4 TECH

DATABASES

Vector similarity search with pgvector, serverless Postgres on Neon, Redis geospatial indexing, and MongoDB.

PostgreSQL (pgvector)MongoDBNeonRedis
DOMAIN 04/ RAG, AGENTS, MCP & WORKFLOWS
7 TECH

AI & AUTOMATION

Engineering cited-answer RAG systems, autonomous AI agents, Model Context Protocol (MCP) integrations, n8n workflow automation, and multi-model LLM pipelines.

RAG SystemsAI AgentsMCPn8n Workflow AutomationOpenAI APIGemini APIGroq API
DOMAIN 05/ INFRASTRUCTURE, CI/CD & DEPLOYMENT
7 TECH

CLOUD & DEVOPS

AWS cloud services (EC2, S3, IAM, VPC, Lambda), Docker containerization, GitHub Actions CI pipelines, and Vercel deployments.

AWS (EC2, S3, IAM, VPC, Lambda)DockerGitHub ActionsVercelGitGitHubPostman
SECTION 06/ Experience & Journey

THE
JOURNEY.

Chronological record of software engineering education, professional internship experience, certifications, and production milestones.

01/ EXPERIENCE
2026
Crixsoft • Peshawar, Pakistan

Software Development Intern

Built and maintained features in real client web projects using React.js and Node.js. Delivered work on schedule through close collaboration with a professional development team.

React.jsNode.jsClient Web ProjectsTeam Collaboration
02/ CERTIFICATIONS (COURSERA)
2026
AWS & LearnKartS | Coursera

4 Cloud, RAG, MCP & n8n Certifications

Completed AI Automation Engineer with n8n Specialization (7 courses, Sep 2026), AWS Fundamentals Specialization (3 courses, Aug 2026), Build Production AI Agents with RAG and MCP (Jun 2026), and Agentic AI Foundations with MERN, RAG and MCP (2026).

n8n (7 Courses)AWS Fundamentals (3 Courses)RAG & MCPAgentic AI
03/ DEPLOYED PROJECTS
2025—26
8+ Deployed Web & AI Applications

Full Stack & AI Production Systems

Built and deployed RAG Document Q&A (page-level cited answers on a $0 stack, 30+ unit tests, Docker, GitHub Actions CI), RideShare (Redis geospatial index, WebSockets, 5-state ride lifecycle, Mapbox, Stripe), MCQForge (Automated Document-to-MCQ Assessment Platform with Upstash Redis Lua, 113+ Vitest tests, Playwright E2E), AI Cold Email Automation (n8n + Groq), and E-Commerce Platform (Auth.js, Prisma, JWT/bcrypt).

Next.jsTypeScriptPostgreSQL (pgvector)RedisDockerGitHub Actions
04/ EXPERIENCE
2024—NOW
CGBZ Society, CUSIT

Web Developer

Developed and maintained web projects for the university's technical society as part of a team and participated in tech competitions and events.

Web DevelopmentTechnical SocietyTech Competitions
05/ EDUCATION
2024—28
City University of Science and Information Technology (CUSIT), Peshawar

B.S. in Software Engineering

Pursuing Bachelor of Science in Software Engineering (2024–2028) at CUSIT, Peshawar, combining core software engineering foundations with full-stack and AI product development.

B.S. Software EngineeringCUSIT Peshawar2024 – 2028
SECTION 07/ Engineering Philosophy

HOW I
THINK.

Four principles that guide every architecture decision, repository, and deployment.

01 — PRINCIPLE

01 — BUILD WITH PURPOSE

Build products that solve actual problems.

02 — PRINCIPLE

02 — ENGINEER FOR SCALE

Think about architecture, reliability, and maintainability.

03 — PRINCIPLE

03 — LEARN BY BUILDING

Use real projects to understand engineering deeply.

04 — PRINCIPLE

04 — EXPLORE WHAT'S NEXT

Experiment with AI, automation, and emerging technologies.

SECTION 08/ PROJECT CONSULTATION
PESHAWAR, PAKISTAN • REMOTE WORLDWIDE

DISCUSS YOUR
NEXT SYSTEM.

Available for custom software builds, RAG knowledge assistants, EdTech/training platforms, and n8n workflow automation for international teams and startups.

[ PROJECT CONSULTATION // DIRECT DISPATCH ]

Start a Project Discussion

24H RESPONSE SLA
Email Directly