Arslan TabishFull Stack Software Engineer
Full Stack Software Engineer

I build web products end to end, from the database to the browser.

Three years shipping production apps on Python, FastAPI, PostgreSQL, React and TypeScript, and increasingly the AI features inside them, for clients, my own products and Intagleo Systems.

View projectsContact
  • 3 years professional experience
  • 30+ projects shipped
  • 10+ happy clients
Available for projects & roles
Portrait of Muhammad Arslan Tabish

Arslan Tabish

Full Stack Software Engineer

Expertise & competencies

Technical arsenal & core skills

The stack I ship with every day, from APIs, data and interfaces to the LLM systems I build into them.

Backend

  • Python 3.12+
  • FastAPI
  • async and await
  • asyncio
  • Pydantic v2
  • SQLAlchemy 2.0 async
  • PostgreSQL
  • WebSockets
  • Background jobs
  • REST APIs
  • API authentication

Frontend

  • React 18 and 19
  • TypeScript
  • Next.js
  • Vite
  • TanStack Start, Router and Query
  • Tailwind CSS
  • Radix UI and shadcn
  • Framer Motion
  • React Three Fiber
  • React Hook Form
  • Zod

Generative AI & LLMs

  • Anthropic Claude API
  • OpenAI API
  • Hugging Face
  • LLM integration
  • Prompt engineering & versioning
  • Structured outputs
  • Context engineering
  • Model routing
  • Prompt caching
  • Token & cost optimisation

Agentic AI

  • Agentic workflows
  • Multi-stage AI pipelines
  • Tool and function calling
  • LangGraph
  • LangChain
  • MCP (Model Context Protocol)
  • MCP tool integrations
  • Claude Code
  • OpenAI Codex
  • Agent memory
  • Multi-agent orchestration
  • Human-in-the-loop

RAG & retrieval

  • RAG
  • Embeddings
  • Vector search
  • Vector databases
  • Semantic search
  • Hybrid retrieval
  • Reranking
  • Chunking & indexing
  • Grounded generation

AI reliability & evaluation

  • Schema validation & retry
  • Output guardrails
  • Automated QA gates
  • Eval harnesses
  • Retrieval evaluation
  • LLM observability
  • Prompt and model evaluation
  • Failure analysis

DevOps & production

  • Docker
  • Vercel
  • Railway
  • AWS S3
  • Cloudflare
  • GitHub and GitLab
  • CI/CD
  • Production monitoring
  • pytest

AI integrations & automation

  • Apify
  • Airscale
  • MillionVerifier
  • Instantly
  • Third-party APIs
  • Webhooks
  • Lead-enrichment pipelines
  • Automated outreach workflows
  • Data extraction & processing

Computer vision

  • OpenCV
  • YOLO
  • Object detection
  • Object tracking
  • Real-time video processing
Interactive portfolio

Featured engineering projects

Full-stack products for clients, my own AI systems and internal platform work, from the data layer up to the interface.

Full-stack AI SaaS · self-built★ Featured
cold-outreach-pipeline.vercel.app
Cold Outreach Pipeline interface

Cold Outreach Pipeline

AI lead-generation SaaS

  • A 9-stage, status-driven, resumable pipeline (extract, enrich, AI filter, gate, email, verify, AI copy, QA, sync) where every lead advances only on a valid stage transition, so runs crash and resume without duplicating work or LLM spend.
  • A defensive structured-output layer wraps every AI call: fence stripping, JSON recovery, schema validation, then a retry with a corrective nudge before it gives up with a typed ParseError. Deterministic guardrails and an automated QA gate catch weak copy before it ever reaches a prospect.
  • Python
  • FastAPI
  • Claude
  • PostgreSQL
  • Stripe
Live siteCode
Freelance project · marketing site
www.khaayaal.com
Khaayaal Elder-Care Platform interface

Khaayaal Elder-Care Platform

Six-route marketing site for an elder-care service

  • Complete six-route marketing site on TanStack Start + Router with React 19 and Tailwind v4, on a custom design-token system and reusable brand component library.
  • Animated 3D hero with React Three Fiber, scene-based scroll animation and an interactive pricing calculator over tiered care plans; React Hook Form + Zod, deployed on Vercel.
  • TanStack Start
  • React 19
  • Tailwind v4
  • Radix UI
  • Vercel
Live siteCode
Enterprise RAG · self-built
DocPilot interface

DocPilot

Permission-aware knowledge assistant over private documents

  • Hybrid retrieval rather than a plain vector lookup: query rewriting and decomposition, dense pgvector HNSW search in parallel with Postgres full-text search, Reciprocal Rank Fusion, cross-encoder reranking and small-to-big section expansion, then token-budgeted packing.
  • Tenant and ACL predicates are compiled into the retrieval SQL itself, backed by Postgres row-level security, so approximate nearest neighbour search can never return a chunk the asker is not allowed to read.
  • Python
  • FastAPI
  • PostgreSQL + pgvector
  • Claude
  • Docker
Code
Freelance project · Figma to production
www.leadsinthepipe.com
Leads In The Pipe interface

Leads In The Pipe

B2B agency website on a serverless API

  • Figma design translated into a production single-page front end on Vite + React 18 + TypeScript with Tailwind design tokens and Framer Motion, backed by a FastAPI serverless API.
  • Vitest + React Testing Library + vitest-axe, a WCAG 2.1 AA pass and SEO work (meta and OG tags, JSON-LD, Core Web Vitals).
  • React 18
  • TypeScript
  • Framer Motion
  • FastAPI
  • Vercel
Live siteCode
Career

Where the work was done

Three years of professional software engineering, shipping full-stack products, APIs and LLM features for real users.

  1. Jul 2024 – Present

    Software Engineer (Full Stack, Python) @ Intagleo Systems

    Lahore

    • Build LLM-powered product features on the Anthropic Claude API: agentic workflows, RAG pipelines, MCP-connected tooling and prompt-engineered integrations. Structured outputs, schema validation and deterministic fallbacks mean the AI features fail safely in production.
    • Ship secure, scalable REST APIs in Python and FastAPI across several production applications, covering authentication, Pydantic validation, background jobs and business logic, plus Django and DRF services with role-based permissions.
    • Design and optimise data across PostgreSQL, MySQL and MongoDB, covering schema design, efficient queries, migrations and data integrity between systems.
    • Deliver full-stack features with React and Next.js front ends against FastAPI services, and real-time WebSocket features for live chat and notifications.
    • Automate internal engineering workflows (task routing, approvals, compliance reporting) in Python, and deliver in Agile teams with Git and GitHub code review, sprint planning and weekly client meetings.

  2. Jul 2023 – Jun 2024

    Associate Software Engineer @ Devsloop

    Lahore

    Delivered full-stack features on client web applications, from ticket through code review to deployment, in a small Agile team.

    • Python FastAPI and Django REST endpoints with React front ends.
    • MySQL and PostgreSQL schema changes, query tuning, bug triage and Git-based team workflows.

  3. Jan 2023 – Jun 2023

    Software Developer Intern @ Wisdom Software House

    Lahore

    Six-month internship building full-stack web applications with a Python FastAPI backend and React front end, and optimising MySQL queries for performance.

Learning path

Still growing

How the stack grew, in the order I learned it. The head marks where I am now.

  1. 01

    Frontend foundations

    • JavaScript
    • React
    • TypeScript
    • Next.js
  2. 02

    Backend & databases

    • Python
    • FastAPI
    • Django REST
    • PostgreSQL
  3. 03

    LLM integration

    • Claude & OpenAI APIs
    • Prompt engineering
    • Structured outputs
  4. 04

    Agentic AI & RAG

    • RAG pipelines
    • LangGraph
    • MCP
    • Evals
  5. 05

    Computer vision

    • OpenCV
    • YOLO
    • Object detection
    • Object tracking
  6. 06Now

    Deep learning fundamentals

    • Neural networks
    • Model training basics
About Arslan Tabish

Real products, built to last.

Building software end to end

I build web applications end to end, the API, the data model and the interface, and more and more the LLM features inside them, and I keep them reliable once they are running in production.

Three years in, I have shipped client sites and full-stack features at Intagleo and Devsloop, built LLM features on the Claude API, and launched Cold Outreach Pipeline as a product of my own. I care most about the unglamorous parts, validation, retries, tests and cost, because that is what makes software, AI or not, survive contact with real users.

Professional experience
3 yrs
Professional experience
Projects shipped
30+
Projects shipped
Happy clients
10+
Happy clients

Education

  1. BSc Computer Science

    University of the Punjab, Lahore

    2020 – 2024

How I work

  • Based in Lahore, Pakistan
  • Production first: validation, retries and fallbacks built in from day one
  • Plain-language updates, honest estimates and demos at every step
  • Working remotely with clients worldwide
Status: Taking on projects, open to full stack & AI roles
Credentials

Certifications & achievements

Course certifications and the competition placing behind the work, each with the skills it covers.

Battle Byte Programming Competition
University level

Runner-Up

Second place at Battle Byte, a university-level programming competition. It was timed, and scored on working solutions rather than elegant ones. That is the same instinct I lean on at work: get something correct and shipping first, then go back and make it fast.

  • Competitive programming
Udemy
Udemy

Python for FastAPI: Advanced Backend Development

Advanced FastAPI: async patterns, dependency injection, authentication and how to structure a project for production. It maps directly onto the FastAPI services I ship at Intagleo and the pipeline behind Cold Outreach Pipeline.

  • FastAPI
  • Async Python
Udemy
Udemy

Python for Computer Vision and Deep Learning

OpenCV, deep learning fundamentals, and image and video pipelines. This is the grounding behind the computer-vision side of my skill set: object detection, object tracking and real-time video processing.

  • OpenCV
  • Deep learning
Anthropic
Anthropic Academy

Claude Code 101

How to work with Claude Code as an engineering tool: codebase exploration, planning before editing, and running agentic changes that stay reviewable. It is the same workflow behind the MCP-driven layout tooling at Intagleo and how I build my own products.

  • Claude Code
  • Agentic coding
Feedback

Do not take my word for it.

What clients, managers and collaborators have said about working with me.

01 / 03

“Arslan took our Figma design and turned it into a fast, polished production site without us having to chase anything. Clear updates, sensible questions early, and the finished site matched the design down to the details.”

Umair Ehsan

Client, Leads In The Pipe

Website build
Get in touch

Let's build together

Have a web app, API or AI feature that needs to hold up in production? I take on client projects end to end, and I am open to full-time full stack and AI engineering roles, remote or on site.

Availability
Lahore · working remotely worldwide · projects and full-time roles