Case File //Ahmad Kaleem Bhatti // AI Engineer

Ahmad Kaleem Bhatti

AI ENGINEER

I build AI applications, agentic systems, and the backend systems behind them. Computer Science student at Air University in Islamabad, Pakistan.

View Case Files Get in Touch LinkedIn GitHub

Personnel File

I build backend systems and applied AI infrastructure. While completing a Computer Science degree at Air University Islamabad, I build independent products to solve specific operational problems. Python and Go handle the backend. TypeScript and Flutter handle the interfaces.

Before Actsurance, I built Qualix AI to address lead leakage in messaging workflows. The system uses a RAG pipeline backed by LangChain and ChromaDB to retrieve relevant business context before qualifying a lead. The backend runs on FastAPI and PostgreSQL, with Celery and Redis handling the asynchronous processing that LLM calls require.

Outside of independent projects, I currently intern at Kaar-e-Kamal Welfare Foundation as an Application Developer Intern. I built the MVP of their Flutter and Go welfare platform, and now lead a team taking it to production. I also intern at Demetronics as a Full Stack Engineer Intern, where I recently migrated a decentralized IoT platform to a secure, centralized Express API. Everything points toward building production-grade, reliable systems as an AI Engineer and Backend Engineer.

I am currently completing my Bachelor of Science in Computer Science at Air University Islamabad (Expected Sep 2028). To further my technical foundations, I've completed certifications in Object-Oriented Data Structures in C++ (Coursera, UIUC), Fundamentals of Generative AI (Microsoft Learn), and CS50x (Harvard, edX).

Good engineering decisions are usually boring to describe. They involve choosing the option with fewer moving parts, writing things that are easy to change, and being honest about what you do not know yet.

GitHub Activity

Methods &
Tools

01

Backend Systems

APIs, layered architecture, background daemons, rate limiting, RBAC.

GoPythonC++FastAPIExpress.jsREST APIsPostgreSQLMySQLRedisFirebaseSupabaseCeleryDockerRBACGitHub ActionsCI/CD

Qualix runs on FastAPI with async SQLAlchemy, PostgreSQL, PgBouncer, Redis, and Celery. The Kaar-e-Kamal welfare platform API is written in Go using pgx for database access and golang-jwt for token validation.

02

AI Applications

Retrieval-augmented pipelines, tool calling, multi-provider LLM orchestration.

PythonLangChainRAGOpenRouterChromaDBTool CallingAI AgentsCursorDevinClaudeCodexAntigravity

The Qualix AI RAG pipeline uses LangChain and ChromaDB to retrieve relevant business context before each inference call. Integrating AI tools like Cursor, Devin, and Antigravity accelerates the path from design to production.

03

Mobile & Frontend

Mobile applications, web dashboards, responsive UIs.

JavaScriptTypeScriptReactNext.jsFlutterTailwind CSSBootstrapGitGitHub

Built cross-platform apps for Kaar-e-Kamal and PakLand. Web dashboards for Qualix AI are built with React and TypeScript, leveraging modern styling frameworks for responsive layouts.

Work History

Building, learning & evolving...

Aug 2026 - Sep 2026On-site · Islamabad

Full Stack Engineer Intern

Demetronics (Private) Limited

Situation

A live IoT platform had exposed database credentials and JWT keys in the codebase, no centralized authorization model, and a mobile app that dropped usage history because it only wrote to local device storage.

Action

Audited legacy systems to secure exposed secrets into environment variables. Architected a migration from decentralized client writes to a centralized Express API, implementing idempotent routes for device management. Introduced RBAC via Firebase Custom Claims. Redesigned the Flutter app's device service to provide offline local-IP fallback when the cloud API is unreachable.

Outcome

Closed a live credential exposure across the platform, delivered a scalable Admin Portal for remote device management, and resolved the data-sync flaw that had been losing usage history on mobile.

Jul 2026 - Aug 2026Hybrid · Islamabad

Application Developer Intern

Kaar-e-Kamal Welfare Foundation

Situation

The foundation managed charity applications and field verifications entirely on paper. Field workers often operated without internet, and there was no way to prevent duplicate aid requests.

Action

Built a Flutter app and a Go API from scratch. Wrote a local syncing service so field workers could queue data offline. Moved approval logic and request limits directly into PostgreSQL constraints, locks, and RLS policies to stop race conditions.

Outcome

Replaced paper records with a working digital system. Field workers can now submit verifications offline, and the database strictly blocks duplicate requests across five user roles.

Feb 2026 - May 2026Part-time · Islamabad

Sales & Data Assistant

Atif E-Commerce Services

Situation

Inventory updates and customer communications across Amazon and eBay were handled manually. The volume of data made consistent accuracy difficult to maintain.

Action

Wrote Python scripts using Pandas and Openpyxl to automate cross-platform inventory synchronization. Built a local desktop interface so non-technical staff could trigger the scripts without using a terminal. Added an LLM classifier to categorize incoming support emails before they reached the team.

Outcome

Listing update time dropped by 35 percent. Support triage speed improved by 45 percent. Manual data correction work decreased by half.

Leadership

Guiding teams & building community...

Nov 2024 - PresentOn-site · Islamabad

Senior Lead Developer

AUCIS (Air University Computing and Innovation Society)

Situation

The computing society needed technical leadership to organize student engineering projects and bring junior developers up to production standards.

Action

Joined as a developer and focused on shipping internal tools and mentoring newer members. Promoted to Senior Lead Developer in April 2026 based on these contributions.

Outcome

Technical direction for all student-led engineering initiatives is managed under this role.

Jul 2026 - Aug 2026On-site · Islamabad

Management Team

Rizq

Situation

A social-impact program in Islamabad built around a 'Three Zero' theme. Intern teams had intense 10–12 day sprints to build real software solutions to local problems, featuring high-profile guest sessions from organizations like WWF-Pakistan and UNICEF.

Action

Served on the management team handling program logistics (scheduling, venue, activities) and directly coordinated and mentored specific intern teams throughout their technical sprints.

Outcome

Facilitated a structured environment where intern teams successfully shipped real solutions under strict deadlines.

CASE 01 / 06

Kaar-e-Kamal

CASE // ASSET

01ALLOW

Kaar-e-Kamal

Challenge

Welfare foundations rely on manual, paper-based workflows for aid distribution, leading to inefficiencies, duplicate approvals, and poor auditability.

Investigation

Kaar-e-Kamal is a digital welfare platform that manages assistance cases from initial application through field verification and final approval. The system gives applicants, field workers, operations staff, and administrators specialized workflows. It enforces business rules, role-based access, and offline synchronization for field operations.

Architecture

Concurrency control prevents duplicate case approvals by serializing requests based on the applicant's identity and case type.

Outcome

ALLOW - Core product built and successfully transitioned from initial MVP into a production system.

Qualix AI

CASE // ASSET

02ALLOW

Qualix AI

Challenge

Sales teams lose deals when they fail to respond quickly on WhatsApp, Instagram, and Telegram. Manual follow-up does not scale, and generic autoresponders fail to qualify leads.

Investigation

Qualix was built to automate lead qualification across WhatsApp, Instagram, and Telegram using an agentic pipeline. When a message arrives, the system retrieves relevant business context using a RAG pipeline, evaluates the buyer's intent, and either qualifies the lead or routes it for human follow-up. The backend exposes tool-calling endpoints that the agent uses to read CRM state, update records, and schedule callbacks without human intervention.

Architecture

The RAG pipeline uses LangChain and ChromaDB. At query time, the pipeline retrieves chunks of business context before passing them to the model. This keeps the context window focused on relevant data rather than loading the full business knowledge base.

Outcome

ALLOW - Backend is built and tested. The CI pipeline enforces code quality. Production performance metrics have not yet been collected.

Demetronics

CASE // ASSET

03ALLOW

Demetronics

Challenge

IoT device fleets controlled via decentralized client-writes face security vulnerabilities, lack global audit trails, and are difficult to manage centrally.

Investigation

A smart water management IoT system connecting mobile controls, a web portal, and backend services. The mandate was to move device control from decentralized mobile apps to a centralized backend architecture, enforcing strict authorization and complete auditing.

Architecture

Replaced direct device writes with a centralized API that requires all device control and scheduling to pass through it.

Outcome

ALLOW - Architecture shift successfully routed device control through a centralized, auditable backend.

PakLand

CASE // ASSET

04ALLOW

PakLand

Challenge

Pakistani real estate platforms have a trust problem. Buyers encounter fake listings, outdated prices, and sellers who have already sold the property. Manual moderation does not keep up.

Investigation

PakLand is a cross-platform Flutter application that treats data accuracy as an engineering constraint rather than a moderation problem. The system enforces listing freshness with an automatic expiry rule, runs AI-based content scanning through an n8n workflow, and calculates a Trust Score for each seller. Search ranking is tied to the Trust Score, which means low-trust sellers cannot game visibility through posting volume.

Architecture

Every listing expires automatically after 30 days. Sellers must re-verify to keep it active. This forces the catalogue to reflect the current state of available properties rather than accumulating stale entries.

Outcome

ALLOW - Completed as an academic project. Authentication, AI moderation pipeline, Trust Score, geo-search, and property booking are all implemented.

GradePilot

CASE // ASSET

05ALLOW

GradePilot

Challenge

The university portal calculates CGPA incorrectly and gives students no way to simulate the effect of retaking a course before committing to it.

Investigation

GradePilot is a client-side Chrome extension that parses the student's grade report from the university portal and recalculates CGPA and SGPA using the correct retake-replacement rules. It also provides a simulation interface where students can test different retake scenarios and see their projected GPA before making enrollment decisions. All processing happens in the browser. No data leaves the device.

Architecture

The calculation engine implements the university's retake-replacement policy exactly. When a student retakes a course, the higher grade replaces the original in the GPA calculation. Non-credit courses are excluded. The engine handles this correctly; the portal does not.

Outcome

ALLOW - Version 1.0 released via WinGet, Inno Setup, and ZIP. Full simulation, planning, and export features are working. Verified adoption data is not available.

QEC Auto-Filler

CASE // ASSET

06ALLOW

QEC Auto-Filler

Challenge

Air University requires students to complete multi-page course evaluation forms before they can view their final grades. The forms are mandatory, repetitive, and contribute no academic value to the student.

Investigation

This extension was built during finals week to automate the evaluation forms. A content script runs on the university portal, detects the form fields, and fills them with pre-configured default answers. An autonomous loop mode processes all subjects in sequence without requiring the student to intervene between forms.

Architecture

A content script identifies evaluation form fields in the portal DOM and populates them with the student's pre-configured answers.

Outcome

ALLOW - Adopted by over 1,000 students within days of release.

Chess Engine

Strategy

Play Chess against a computer that thinks multiple steps ahead to outsmart you.

Play the computer
Watch Auto-Play
Adjust Difficulty

Connect 4

Adversarial

Drop your chips and try to beat a computer programmed to predict and block your every move.

Play the computer
Watch Auto-Play
Zero-Sum Game

2048

Probabilistic

Watch the computer automatically solve the 2048 puzzle by calculating the safest moves.

Watch Auto-Play
Grid Logic
High Scores

Snake

Pathfinding

Watch the snake autonomously navigate the board to find food without crashing.

Watch Auto-Play
Real-Time Pathing
Collision Avoidance

Minesweeper

Logic

Let the computer safely flag mines for you using pure logic and probability maps.

Play the computer
Watch Auto-Play
Safe Sweeping

Launch Games Lab →5 interactive environments · automated opponents · contact panel

Open to AI Engineering, Backend Engineering, and Agentic AI roles.

Send Email ↗LinkedIn ↗Games Lab ↗

Get in Touch