Yo, I'm
Come look around, I promise it's not all tech stuff.
i'm ahnaf. i'm 23. i love building stuff. sometimes it works, sometimes it doesn't.
i don't really do things one at a time. i think the early phase of building anything, a product, a skill, a decision, is supposed to be chaotic. three things moving at once, messy, overlapping. the craft isn't in doing one thing well in isolation. it's in pulling multiple moving parts together into something that produces more than what you put in.
i need to understand things. not surface-level, not “i read a blog post.” i mean actually get it. i'll tear something apart just to see how it works, whether that's a system, an argument, or a problem i probably should've left alone.
i'm fast. i'll get a whole day's worth of work done in a few hours. and when i go off-script, that's usually when the best ideas show up. i just prioritize whatever's working in my head at the time. i'll somehow always manage to be late though, unless it's life or death.
i like people who don't perform. no bullshit, no act that's going to fall apart in six years. if you work hard, work hard. if you're having fun, have fun. just be the same person either way.
most of my friends just come to me when they want to talk, or when they want the truth and not the comfortable version of it. outside of that i'm pretty chill. i'll put music on, go for a late night drive and eat mcdonalds, and not think about anything for a while. i care about dumb things like labels being peeled off stuff in public. i don't know why. it just shouldn't happen.
i like failing. not in a motivational poster way. if my first instinct is wrong, that usually means most people's first instinct is wrong, or my world view was completely fucked, which means it's not an easy problem, which means we might actually be onto something. the best kind of failure is when you fail but you fail with an answer.
CS @ University of Manitoba, graduating December 2026.

what i do when i'm not coding.

"the money pit"

416hp of bad decisions ✓
2008 IS-F
5.0L V8 • 416hp
8-speed paddle shift
tap for the mod list →
Did you know... →
My favorite car was a yellow Volkswagen Beetle.
I don't know what
happened either.
🎧 what i'm listening through
Energy Pro 22s. PSB P5s. Hifiman XS.
i buy old speakers and explain why they're better.
✈️ stamps in the passport
dubai kid. winnipeg by choice.
🇲🇹 🇩🇪 🇬🇧 whenever i can.
"Walk in with confidence"
📌 say something
drop a message, a joke, a hot take.
or just lurk. i respect the lurk. →
"i forgor
🧠 how i work
research until it clicks. execute.
research again because i didn't
trust the first answer.
TODO: stop researching,
just buy it
(never happens)
🧠 the self-aware bit
really into understanding
how my brain works.
has it helped? technically yes.
do i act on it? absolutely not.

I love sunsets.
📍 Dubai, United Arab Emirates
May 2025 — Present| Remote

Featured Project
Contributed to a medium impact open-source project (26.8k stars, 2.6k forks) by implementing the OpenAI o3 function support into the Chatbox application and interface, enhancing AI interaction capabilities. Designed and developed UI components for adding and removing functions, improving user experience and extending functionality for AI enthusiasts and developers. Integrated new features with existing API calls, ensuring backward compatibility while expanding project capabilities.

Featured Project
Streamlined unstructured data organization by implementing BERT embeddings and cosine similarity analysis, optimized through multi-threaded execution on ARM64 architecture, achieving 35% reduction in processing time. Integrated interactive Plotly dashboards to visualize semantic relationships and embedding clusters, enabling efficient pattern recognition and data-driven decision making. Enhanced data classification workflow by engineering an embedding-based comparison system, potentially reducing analysis times by up to 99% in specific use cases while maintaining data integrity.

Featured Project
Developed Athena, an AI application for conversational Google Calendar management. Internal benchmarking and performance analysis position its capabilities among top AI scheduling tools, particularly in reliably executing complex, multi-step commands derived from natural language (92% interaction efficiency). Built the backend infrastructure (Node.js) utilizing PostgreSQL for persistent storage of user profiles, preferences, and conversation history, ensuring accurate context for the AI. Implemented a multi-layer caching strategy (Redis L2, Node-cache L1) to optimize performance by reducing Google Calendar API latency and ensuring rapid data retrieval. Engineered the natural language processing pipeline using a Large Language Model (LLM) to accurately and safely interpret diverse and context-heavy user commands for calendar actions with 98% accuracy. Architected the AI agent pipeline to perform autonomous planning and sequential invocation of multiple tools (function calling) based on conversational context to fulfill complex, multi-step user requests without any extra input from the user.
My inbox is always open. Whether you have a question or just want to say hi, I'll get back to you for sure!