Skip to content
View zyna-b's full-sized avatar
🎯
Focusing
🎯
Focusing
6 followers · 5 following

Achievements

Achievement: YOLO

Achievements

Achievement: YOLO

Highlights

Block or report zyna-b

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
zyna-b/README.md

☕ About me — the short version

name:     Zainab Hamid
role:     AI Engineer @ Liztek
focus:    Agentic systems, Gen AI, Python backends
based_in: Lahore, Pakistan 🇵🇰
fueled_by: cold coffee + a stubborn debugger
mood:     "let's just ship it and iterate"

I take messy real-world data, weird stakeholder requirements, and LLM behavior that nobody fully understands — and turn it into backends that don't fall over on a Tuesday afternoon.

Currently: building multi-agent data quality systems for an enterprise financial product piloting at a top-tier Pakistani bank.

 coding

me, mid-debug, lying to myself
about "one more fix"

🛠️ What's on my desk right now

🏦 Finora

Day job · Liztek

Agentic data quality platform for enterprise finance. Validator → Parser → Anomaly Detection → Resolution agents, all coordinated, all logged, all auditable.

LangGraph · FastAPI · PostgreSQL

💌 Envoy

Side build

WhatsApp-native AI agent that parses Urdu / Hinglish RSVPs (yes, including "Inshallah" and "kal batata hoon") into clean state.

LLMs · WhatsApp API · Cultural NLU

🔍 Delta-1

Personal

Vector search + RAG pipeline that actually returns relevant chunks, not just technically relevant chunks.

Pinecone · LangGraph · Embeddings

🧰 The toolbox

⟶ Languages & Core

⟶ Gen AI & LLMs

⟶ ML / Deep Learning

⟶ Backend & APIs

⟶ Tooling & Infra


📊 The receipts




activity graph



trophies

🐍 Watch my contributions get devoured

snake

🎲 A fact you didn't ask for

"The most dangerous phrase in software is 'it works on my machine.' The second most dangerous is 'the LLM said it would do that.'"

I genuinely believe a good print() statement has resolved more existential crises than any therapist could. The hierarchy of debugging:

print()  →  pdb  →  re-read the docs  →  ask the LLM  →  cry
                                                ↑
                                  (this step is non-optional)

Three things I'll always pick:

  • ☕ Cold coffee over hot tea — fight me
  • 🐍 Python over almost anything (sorry JavaScript, you tried)
  • 🎯 Shipping a 70% solution today over a 100% solution in three months

🤝 Let's talk

I'm always up for a chat about agentic systems, production Gen AI, weird LLM failure modes, or why your retrieval pipeline isn't retrieving.



footer

made with too much coffee and a slightly overconfident commit message ☕ · Lahore, PK

Popular repositories Loading

  1. React-GSAP-Animated-Studio-website React-GSAP-Animated-Studio-website Public

    React + GSAP implementation of ThirtySixStudio's animated UI. Features interactive elements, canvas animations, and smooth scrolling for an immersive web experience. Built with React 19, GSAP, and …

    JavaScript 5 1

  2. Food-Recommendation-System Food-Recommendation-System Public

    A hybrid machine learning recipe recommendation system using collaborative filtering and content-based filtering on the Food.com dataset.

    Jupyter Notebook 4

  3. Real-Time-Emotion-Detection Real-Time-Emotion-Detection Public

    “Real-time facial emotion recognition (OpenCV + TensorFlow, FER2013) with webcam visualization”

    Python 3 1

  4. Zainab-Hamid Zainab-Hamid Public

    TypeScript 1

  5. DSA-Mentor-Telegram-Bot DSA-Mentor-Telegram-Bot Public

    A Python-based Telegram Bot for task automation and chatting.

    Python 1

  6. Face-Emotion-Detector-using-CNN Face-Emotion-Detector-using-CNN Public

    🎭 Real-time facial emotion detection using CNN trained on FER2013 dataset. Built with TensorFlow & Streamlit. Detects 7 emotions: Angry, Disgust, Fear, Happy, Sad, Surprise, Neutral. Live demo avai…

    Jupyter Notebook 1 1