Sharaheel Ali
Hello, I'm

Sharaheel Ali

I'm a AI Engineer in Training
Scroll
About Me

Hi, I'm Sharaheel — or Shar for short.

I'm a Computer Science student at the University of Illinois Chicago building AI systems people can trust — with security as the lens I bring to every build. This portfolio documents what I'm building, how I verify it, and where I'm headed.

Builder by Curiosity

I learn by building.

I like turning ideas into low-stakes prototypes I can test and improve — a Calendar AI assistant, a chess minigame, and this WordPress portfolio. Shipping something small teaches me more than reading about it.

Competitive by Nature

Focus under pressure.

I'm a 1700 Elo, state-level chess player, and I play CS, Valorant, and Fortnite. Competition taught me focus, fast adaptation, and how to learn from losses instead of avoiding them.

Building Toward AI Engineering

A clear target.

I'm targeting AI engineering — working through a self-directed arc from tokenizers to a tiny transformer to RAG from scratch, and closing the gaps real job postings exposed: RAG and vector databases, cloud platforms, and orchestration frameworks. My security training stays the foundation for building AI safely.

Resume

Education, skills & experience.

Download Resume ↓
Education

University of Illinois Chicago

B.S. Computer Science, College of Engineering
GPA 3.76 · Dean's List · Expected May 2029

Program Design I - II Calculus I - III Applied Statisics Computer Organization Foundations Of Computing
Technical Skills

Languages

PythonJavaScriptSQLHTML / CSS

Frameworks & Tools

FlaskReactElectronGoogle Calendar API / OAuthREST APIsPython TurtleWordPressGit & GitHubVS Code

AI Engineering & Security

Agentic AI ArchitecturesEval HarnessesPrompt EngineeringLinuxSIEMThreat ModelingVulnerability AssessmentIncident ResponseResponsible AI Workflows
Experience
Instructor Code Ninjas

Teach coding fundamentals and problem-solving to young students, breaking technical concepts into clear, approachable steps.

AI Leaders — Top 40 Finalist & Product Feedback WordPress Foundation

Selected as a Top 40 finalist in Cohort I; built portfolio artifacts and contributed product feedback on AI-assisted WordPress workflows.

Sales & Profit Analyst Alwahid Tandoor Express

Analyzed sales and profit data to support business decisions and identify trends.

Retail Data & Operations Urban Styles

Handled retail data and day-to-day operations, keeping records organized and accurate.

Certifications
Google Cybersecurity Certificate
CodePath — Intro to Cybersecurity
Anthropic AI Fluency
Anthropic Claude 101
AI Leaders — Cohort I
Non-Negotiables

Three filters I run every posting through before I apply.

Real data, not demos 01

Does the role put AI in front of live user data or systems, or is it internal prototypes and demos?

Verification as first-class 02

Do their public materials, GitHub, or posting mention testing, evals, reliability, or internal quality standards?

AI-native, not bolted-on 03

Is AI the core product, or a feature getting added to an existing app?

Projects

Technical Projects & AI-Built Work

A focused collection of AI, software, WordPress, and interactive app projects that show how I build, verify, and ship practical tools.

Featured Project

Timely AI Calendar Assistant

Timely AI is an agentic scheduling assistant I built with React and Flask. It connects to Google Calendar, classifies every request into one of five intent types, runs the result through a deterministic validation layer, and confirms with the user before anything is written to their calendar.

I proved it works with a 42-case eval harness scoring 98% overall — including driving cancel-intent accuracy from 33% to 98% after reworking intent handling. This project demonstrates agentic architecture, eval-driven development, and user-focused design.

Agentic AI Google Calendar Eval Harness Full-Stack Project

What this project shows

  • Five intent types with deterministic validation
  • Confirm-before-write calendar safety
  • 42-case eval harness — 98% overall
  • Cancel intent: 33% → 98% after an intent-handling rework
  • AI chat panel for natural-language scheduling
Functionality demo showing calendar questions, availability checks, and natural-language scheduling.
Timely AI dashboard showing a monthly calendar, scheduled events, and an AI calendar assistant chat panel.
Full Timely AI dashboard with calendar events, monthly view, event cards, and the AI assistant panel.
Timely AI login screen with Google sign in.
Login screen where users connect their Google Calendar.

Why this project matters

The demo version of an AI assistant is easy; the hard part is trusting it with someone's live calendar. Timely AI is where I proved I could do that — intent classification, deterministic validation, confirm-before-write, and a scored eval harness that turned "it seems to work" into numbers. It's the clearest evidence of how I want to build AI systems.

Problem

Scheduling can feel scattered when users have to search events or create meetings manually.

Solution

An agentic assistant that classifies intents, validates deterministically, and confirms before writing.

Verification

A 42-case scored eval harness measured real behavior — 98% overall, cancel intent 33% → 98%.

What I Learned

Evals beat vibes — scoring the system is how I found and fixed the cancel-intent failure.

Interactive App Project

Aim Trainer Reaction Game

This Aim Trainer is a simple reaction-based desktop app I built to help users practice speed, accuracy, and consistency. The user clicks randomly placed targets while the app tracks points, streaks, average reaction time, and time remaining.

I kept the design intentionally clean and focused. The app includes a settings menu where users can switch between Simple and Stats mode, choose 30-second, 60-second, or Infinite play, and pause the game without losing the visual style of the app.

Reaction Game UI Design Performance Tracking Electron App

What this project shows

  • Interactive target-clicking game logic
  • Points, streaks, and average reaction tracking
  • Simple and Stats display modes
  • 30-second, 60-second, and Infinite timer options
  • Clean settings menu and pause overlay
Demo showing the Aim Trainer's target-clicking gameplay, settings menu, timer modes, and performance tracking.

Problem

Reaction games need to feel fast, readable, and uncluttered so users can focus on performance.

Solution

I built a clean aim trainer with targets, scoring, streaks, timers, and a simple settings menu.

Design Choice

I kept the interface minimal so the game feels easy to understand and quick to play.

What I Learned

This helped me practice interactive UI logic, state management, timing, and user-focused design.

CS 111 Exemplary Project

Mate in 10! Chess Puzzle Minigame

Mate in 10! was my CS 111 final project, built with Python Turtle. The game starts with a Learn Mode that teaches chess piece movement, then moves into a 10-puzzle practice run where users solve tactics from easy to hard.

My group earned an exemplary grade on this project. It shows my ability to build a larger interactive Python program with visual design, event handling, game logic, feedback, scoring, timing, and a polished user flow.

Python Turtle Game Logic UI Design Exemplary Grade

What this project shows

  • Interactive Python Turtle interface
  • Learn Mode for chess movement practice
  • 10-puzzle run with tactics and difficulty progression
  • Timer, misclicks, clean solves, and best-run tracking
  • Clear feedback screens and replay options

Problem

Chess tactics are harder to learn without interactive practice, feedback, and progression.

Solution

We created a minigame that teaches movement and then challenges users through 10 puzzles.

My Role

I helped shape the interface, gameplay flow, puzzle structure, debugging, and polish.

What I Learned

This strengthened my Python, event handling, UI layout, testing, and project organization skills.

WordPress Development

Portfolio Website Iteration

This before-and-after comparison shows how I used WordPress and AI-assisted iteration to make my portfolio cleaner, more organized, and more professional.

Before, the site had the basic information, but the layout felt plain and harder to scan. After using WordPress customization and AI-supported feedback, I improved the visual hierarchy, navigation, spacing, buttons, theme consistency, and overall presentation.

WordPress AI-Assisted Iteration Visual Polish Portfolio Design

What changed

  • Cleaner navy visual theme
  • More professional homepage layout
  • Clearer navigation and buttons
  • Stronger personal branding
  • Better alignment with AI Leaders portfolio expectations
Before Earlier version of the portfolio website with a simpler white layout.
Earlier portfolio version with basic structure but less visual polish.
After Updated portfolio homepage with navy theme, centered hero section, profile image, and clean navigation.
Updated version with a cleaner WordPress layout, stronger theme, and better presentation.

Problem

The original site was functional but looked plain and did not fully communicate my goals.

Process

I used AI feedback to plan improvements, then applied the changes myself in WordPress.

Result

The final version feels cleaner, more professional, and easier for reviewers to navigate.

Skills Shown

WordPress design, page structure, visual hierarchy, content organization, and iteration.

AI Leadership

AI Verification Workflow

A workflow showing how I use AI responsibly by checking claims, comparing sources, revising outputs, and using AI as a support tool instead of a shortcut.

Skills shown: AI ethics, verification, research, reflection, responsible AI use, and clear communication.

View AI Workflow →
Career Readiness

Resume & Technical Direction

My resume and portfolio connect my Computer Science background with AI engineering, agentic systems, security fundamentals, and responsible AI-assisted work.

Skills shown: communication, career alignment, project explanation, and professional presentation.

View Resume →
AI Leaders · Cohort I · 2026 — Top 40 Finalist

From lessons to proof. My AI Leaders map.

Top 40Selected as a finalist in AI Leaders Cohort I.
~500Participants the cohort was drawn from.
5Core artifacts built and documented.
1 liveWordPress portfolio presenting the work.

AI Leaders pushed me past "using AI" into working with it responsibly. My workflow became verification-first: I brainstorm and build fast with AI, then slow down to check the important details — testing behavior, reading documentation, and confirming claims before I trust the output.

Across the cohort I produced five artifacts that build on each other — Foundations work that mapped my tools and online identity, AI-leadership pieces on ethics and tool integration, and a career-readiness plan tied to a real Security Analyst path.

The throughline is the same habit I want in AI engineering work: accuracy over speed, and a human staying in the loop on every decision.

01FoundationsTools, tech stack & digital identity audit.
02AI LeadershipPersonal AI ethics criteria.
03Verification WorkflowBrainstorm → build → verify.
04Career-Readiness PlanSecurity Analyst & living-wage plan.
05Live WP PortfolioThis site — the proof, assembled.

The full map walks through every artifact, PDF, and reflection — with the original screenshots and downloadable evidence.

Explore the full AI Leaders Map →
Security Lens

Security is my lens, not my destination.

I keep asking the same three questions about any system: what could go wrong, who's affected, and what's the safer path? These notes track the security foundation I bring to every AI system I build.

What I've Studied

LinuxCommand line, permissions, and navigating a system the way an analyst does.
SQLQuerying data and understanding how databases can be probed or misused.
SIEMReading logs and alerts to spot what looks normal versus suspicious.
Threat ModelingMapping what could go wrong before it does, and where the weak points are.
Incident ResponseKnowing the steps to take when something does go wrong.
Vulnerability AssessmentLooking for gaps and weaknesses in a system on purpose.
Defensive SecurityThinking like a defender — protecting users, data, and access instead of just reacting.

Security + AI Ethics

I treat AI as a helper, not a source of truth. I verify what it gives me, and I never paste private or sensitive data into a tool I don't control. Responsible use is part of security.

What I'm Building Toward

I want to grow into AI engineering work where a verification mindset is the job — checking assumptions, confirming details, and protecting the people behind the system.

AI + Verification Workflow

AI is a thinking tool, not a judgment replacement.

I use AI to think and document more clearly, never to replace my own judgment. I care about accuracy over speed, which means the work isn't done until I've checked it.

01

How I Use AI

  • Brainstorm and explore approaches before building
  • Organize messy notes and next steps
  • Clarify concepts I'm still learning
  • Improve how I communicate and explain my work
02

Verification in Practice

In Timely AI, a user types a request in natural language and the app turns it into a Google Calendar event. Before anything is created, it checks for missing details and asks the user to confirm — AI proposes, the human decides.

03

Why This Matters for My Path

AI engineering depends on not trusting things blindly. The same habit — check the claim, confirm the detail, keep a human in the loop — is how I build systems worth trusting.

04

The Loop

Brainstorm → Build → Verify. I move fast with AI in the first two steps, then slow down to confirm important claims through documentation, testing, logs, or my own reasoning before I trust the output.

Contact

Let's connect.

I'm open to connecting about AI engineering, agentic systems, and internship or early-career opportunities.

© 2026 Sharaheel Ali · Built with WordPress + responsible AI.

Back to top ↑