Part Three · Pages 5 & 6

The Work
That Speaks
Louder

Four production-grade projects. Ten certifications. One year. The ledger of a young engineer who chose to prove himself through output, not credentials.

4 Major Projects
10+ Certifications
97.7% Latency Reduction
94% ML Accuracy Achieved
05
Page Five · The Projects

Four Systems,
Four Frontiers

If the measure of an engineer is not the title they hold but the things they have built and shipped, then Ariyan Nadeem's portfolio speaks with extraordinary clarity. Between July 2025 and January 2026, he built four distinct AI systems — each one targeting a different frontier of applied machine learning, each one demonstrating a level of technical sophistication that would be impressive from a team of experienced engineers, let alone from a self-taught seventeen-year-old operating independently from Lahore. Let us look at each of them closely, because the details matter.

Project 01 · ML Engineer Federated XAI Healthcare Predictor
Jul 2025 – Oct 2025

This project tackled one of the most sensitive intersections in modern AI: healthcare prediction with privacy preservation and model interpretability. Ariyan built an XGBoost-based prediction engine achieving 94% classification accuracy, and then went further — he integrated SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to make every prediction transparent and auditable. The system was also architected as a federated learning setup, simulating training across multiple data nodes without centralizing patient records. This is not a toy project — it addresses real regulatory and ethical concerns in deploying AI in medical contexts.

94% Accuracy SHAP + LIME Explainability Federated Architecture Low-Latency API
Project 02 · Edge AI Engineer Edge-Optimized Voice Intelligence (TinyML)
Aug 2025 – Nov 2025

A CNN compressed to 75KB. A full DSP pipeline with 3ms inference. Complete offline operation. Ariyan designed a keyword-spotting neural network from scratch, then systematically compressed it using INT8 quantization until it fit within an embedded footprint smaller than most web images. The DSP pipeline processes raw audio signals, extracts features, and feeds them through the network — all within 3 milliseconds on constrained hardware. The system requires no internet connection and no cloud backend, making it suitable for deployment in IoT devices, wearables, and edge nodes. The engineering precision required here — balancing model accuracy against memory footprint against latency — is a graduate-level challenge solved without a graduate degree.

~75KB Compressed CNN ~3ms DSP Latency INT8 Quantization Fully Offline
Project 03 · ML Infrastructure Engineer Adversarial ML Governance Engine
Jan 2026

Security for AI systems is an emerging field that most production teams still underinvest in. Ariyan built a defensive ML layer capable of detecting anomalous or adversarial inputs in real time — the kind of system that sits in front of a model and acts as a sentinel against manipulation attempts. He implemented input validation and confidence-check logic with under 3ms latency overhead, and redesigned the pipeline architecture to consolidate multiple models into a single CPU-optimized flow that reduced infrastructure costs without sacrificing detection capability. This project demonstrates security-conscious engineering thinking that goes well beyond typical ML development.

Real-Time Anomaly Detection ~3ms Overhead CPU-Optimized Pipeline Input Validation Layer
Project 04 · AI Systems Engineer ORCHAT — AI Orchestration Framework
Jan 2026

ORCHAT is perhaps Ariyan's most architecturally ambitious project to date. Rather than building another model or another inference pipeline, he built the scaffolding that manages how AI agents coordinate with each other. ORCHAT is a lightweight AI orchestration framework that achieves 16ms startup time and minimal memory usage on Linux systems. It supports modular agent workflows with structured logging and automated documentation, and is packaged as a Debian-compatible CLI tool — meaning it can be installed and operated on any standard Linux machine with a single command. Building an orchestration framework requires understanding not just how individual AI components work, but how they should communicate, fail gracefully, and scale — a systems-level perspective that separates infrastructure engineers from model builders.

16ms Startup Modular Agent Workflows Debian CLI Tool Structured Logging

Taken together, these four projects span healthcare AI, embedded systems, security engineering, and multi-agent orchestration — four of the most active and specialized sub-fields in applied machine learning. No single academic program would cover all four in the same year. Ariyan covered them all because he followed the problems that interested him, not a prescribed curriculum.

06
Page Six · The Credentials

January's
Certificate Storm

January 2026 was, by any measure, a remarkable month in Ariyan Nadeem's already remarkable short career. In the span of a single calendar month — while pursuing his Intermediate Science studies — he completed and received certificates from four of the world's most recognized organizations in technology, data, and business consulting. The pace was extraordinary. The breadth was intentional. And the combination of credentials painted a very specific picture of who Ariyan is becoming: not just an AI engineer, but a multi-dimensional technologist with depth in cybersecurity, cloud architecture, data visualization, and enterprise analytics.

"Seven certifications earned across Deloitte, AWS, TATA, and Google. All within six weeks. All while enrolled full-time in college."

Google / Kaggle
5-Day AI Agents Intensive
December 18, 2025
Google
Generative AI Fundamentals
January 2026
Deloitte via Forage
Technology Job Simulation
January 4, 2026
Amazon Web Services via Forage
Solutions Architecture Job Simulation
January 6, 2026
TATA via Forage
Data Visualisation: Empowering Business with Effective Insights
January 7, 2026
Deloitte via Forage
Data Analytics Job Simulation
January 7, 2026
Deloitte via Forage
Cyber Job Simulation
January 8, 2026
Mindluster
Management Information Systems (Basic)
2025–2026

The crown jewel of these credentials arrived first, in December 2025: the 5-Day AI Agents Intensive from Google and Kaggle. This was not a passive video course — it was a hands-on engineering program focused on agentic AI systems and multi-agent orchestration. Ariyan's capstone submission was an 82-cell system demonstrating a 97.7% reduction in latency through asynchronous execution and optimized reasoning pipelines. He earned the badge under his online identity, Ariyan_Pro, and the achievement is publicly verifiable.

The Deloitte simulations — Technology, Data Analytics, and Cybersecurity — represent something particularly interesting. Deloitte is one of the "Big Four" global consulting firms, and their Forage simulations are designed to mirror real tasks performed by their actual analysts and engineers. By completing tasks in data analysis, forensic technology, cybersecurity operations, and coding development, Ariyan demonstrated that his capabilities are not limited to deep ML research — he can operate across the enterprise technology landscape that large organizations actually care about.

The AWS Solutions Architecture simulation added cloud infrastructure design to his toolkit. The TATA Data Visualisation program developed his ability to translate complex data into clear, decision-driving visuals — a skill that bridges the gap between technical depth and business communication. Together, these credentials tell a story of intentional breadth: Ariyan is not building himself into a narrow specialist. He is building toward the kind of full-spectrum technical capability that makes someone genuinely indispensable.