Skip to content
View Nimra3261's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report Nimra3261

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
Nimra3261/README.md

👋 Hi, I'm Nimra Khalid

AI Engineer · Agentic AI · NLP · Computer Vision

Typing SVG


Portfolio LinkedIn Email


🧠 About Me

class NimraKhalid:
    def __init__(self):
        self.name        = "Nimra Khalid"
        self.role        = "AI Engineer"
        self.location    = "Islamabad, Pakistan 🇵🇰"
        self.education   = "BS Artificial Intelligence — SZABIST (CGPA: 3.68/4.0 🥈 Silver Medalist)"
        self.seeking     = "Exciting AI Engineering opportunities 🚀"
        self.focus       = ["Agentic AI", "NLP", "Computer Vision", "LLMs", "Data Pipelines"]
        self.email       = "nimra3261@gmail.com"

    def say_hello(self):
        print("Let's build something intelligent together! 🚀")

me = NimraKhalid()
me.say_hello()

🚀 What I Build

🤖 Agentic AI Systems

Custom agent-loop frameworks enabling LLMs to reason, select tools, and execute tasks autonomously — with tool registries, prompt orchestration, and observation handling.

🗂️ Multimodal Pipelines

End-to-end data ingestion processing audio, images, PDFs, and text into structured training datasets using LLaMA, LLaVA, and other multimodal models.

👁️ Computer Vision

Real-time object detection and segmentation systems — from construction safety monitoring to fruit detection with YOLOv8.

🔍 Semantic Search & NLP

Embedding-based document retrieval using FAISS without LLMs, plus NLP-powered recruitment systems that parse CVs and rank candidates.


🛠️ Tech Stack

Languages

Python MySQL Laravel

AI / ML

TensorFlow OpenCV Streamlit Jupyter

Tools

GitHub VS Code Netlify


💼 Experience

Role Company Period
🤖 AI Engineer RCM Nexus Jul – Dec 2025
🧠 AI / ML Engineer Biome Jul – Oct 2025
🔬 AI Engineer Intern Disruptive AI Jun – Sep 2024

📌 Featured Projects

Retrieval-augmented document Q&A — FastAPI backend, ChromaDB vector store, Claude API generation, React frontend. Ships with a retrieval-quality eval harness (hit@3: 90%) that gates CI, and 28 tests exercising real embedding-based retrieval rather than mocks.

RAG FastAPI ChromaDB Claude API React CI/CD pytest

A decoder-only transformer with hand-written causal self-attention — no nn.MultiheadAttention, every matmul and mask is explicit. Trained character-level on Shakespeare's complete works (loss 4.56 → 1.61 over 2000 steps), with a test that proves zero future-token leakage rather than just checking output shapes.

PyTorch Transformers Streamlit pytest

Researcher, writer, and critic agents hand off work in sequence with live SSE streaming — the critic checks every claim in the draft actually traces back to the research brief and triggers a real revision when it doesn't. Next.js + TypeScript, new stack for this portfolio.

Next.js TypeScript Tailwind Groq Vitest

Plans a question into sub-questions, researches each with live web search, and synthesizes one answer where every claim cites the source that actually supports it — pulled from real search results, never invented.

Agentic AI Claude API Python pytest

End-to-end recruitment platform — job postings, GPT-4 resume screening against the job description, interview panel scheduling and evaluation, personality assessment, and offer letters, with role-based dashboards for HR, HOD, and Dean.

Laravel PHP Python Flask GPT-4 MySQL FYP

Three models compared honestly on cross-validated ROC-AUC (logistic regression won), with SHAP explaining each individual prediction rather than just outputting a number.

scikit-learn SHAP Streamlit Python

Real-time fruit detection and classification using YOLOv8. Full pipeline from dataset prep to model inference.

YOLOv8 Computer Vision Python


🌱 Open Source Contributions

Repo Pull Request Status
chroma-core/chroma Ban relative imports via flake8-tidy-imports Open
chroma-core/chroma Fix vacuous-pass test assertions in add.collections tests Open
chroma-core/chroma Use rejects.toBeInstanceOf instead of manual sentinel in admin test Open
Unstructured-IO/unstructured Add right-to-left reading order support to xy-cut sorting Open
anthropics/claude-cookbooks Cookbook notebook contribution (PR #790) Open

🏆 Certifications & Awards

Award
🥈 Silver Medalist — Top Graduate, SZABIST Islamabad (2025)
🌐 Microsoft Learn Student Ambassador (MLSA) — SZABIST
⚙️ Agentic AI Engineering — Professional Certification
🤖 Generative AI For Everyone — DeepLearning.AI
📐 Machine Learning Specialization — Andrew Ng, Coursera

📫 Let's Connect

I'm actively seeking exciting AI Engineering opportunities — open to relocation.

Portfolio LinkedIn Email


"Let's build something intelligent together 🚀"

Pinned Loading

  1. groundtruth groundtruth Public

    Research agent (plan -> research -> synthesize) using Claude web_search + web_fetch, with claim-level citations pulled only from real search results

    Python

  2. HireSmart HireSmart Public

    Recruitment platform - job postings, GPT-4 resume screening, interview panel scheduling, personality assessment, and offer letters, with role-based HR/HOD/Dean dashboards

    Blade

  3. dociq dociq Public

    RAG document Q&A — FastAPI + ChromaDB + Claude, with a retrieval eval harness gating CI (hit@3: 90%)

    Python

  4. agent-pipeline agent-pipeline Public

    Three agents hand off work (researcher -> writer -> critic) with live SSE streaming; the critic checks every claim in the draft actually traces to the research brief

    TypeScript

  5. nanoglyph nanoglyph Public

    A decoder-only transformer built from scratch (hand-written causal self-attention), trained character-level on Shakespeare's complete works.

    Python 1