~/khizer/index.html

Muhammad Khizer Tariq

AI engineer & researcher — continual learning, applied ML, LLM systems

email·github·linkedin·scholar·cv.pdf

about

$ whoami

AI engineer working on applied LLM systems and automation, and a researcher with an ongoing interest in continual learning, optimization, and applied ML. BS in Computer Science, NUST Islamabad, 2025. Most of what's below is either published, deployed, or both — I've tried to keep this page closer to a changelog than a pitch.

$ echo $OFF_HOURS

Reading, football (soccer), cricket, and slowly working through Spanish.

research & publications

Enhancing Vehicle Routing with Time Windows: A Machine Learning-Driven Ant Colony Optimization Approach Dec 2024

FIT 2024 · First author

Route optimization algorithm integrating ant colony optimization with machine learning; grew out of the final year project below.

Grouped Matrix Clocks with Reduced Complexity for Distributed Synchronization Dec 2024

International Journal of Computer Applications · First author

A group-based matrix clock algorithm that reduces space complexity while preserving causality tracking.

Breast Cancer Detection through Spectrogram Generation from GAN-Simulated Microwave Imaging Data Apr 2025

ICMAC 2025 · First author

Detection pipeline built on microwave imaging data augmented via GANs and deep learning.

experience

AI Engineer — Antematter May 2025 – present
  • LLM-powered automation workflows for client audit, reporting, and outreach pipelines
  • Technical evaluation and proposal design for client automation systems
  • Reliability audits of production multi-agent AI systems
Research Assistant — Machine Vision & Intelligent Systems Lab, NUST Oct 2024 – Aug 2025
  • Mitigating catastrophic forgetting in continual learning for robotics and healthcare applications
  • Authoring a survey paper on continual learning methods
Research Assistant — High Performance Computing Lab, NUST Jan 2024 – Dec 2024
  • NLP methods for chatbot dialogue coherence; fine-tuned LLMs for dialogue management
Research Intern — Optical Networks and Technologies Lab, NUST Jun 2024 – Sep 2024
  • Seismic activity detection via distributed fiber optic sensing, using LSTM-based time series models

projects

FinRAG-MCP 2026

MCP server combining local RAG search over SEC-style filings (sentence-transformers, ChromaDB) with live market data tools. Includes a retrieval eval suite (hit-rate@3, MRR, recall@5).

Routing through Satellite Imagery — Final Year Project 2024–2025

Extracting roadway networks from satellite imagery and routing for remote areas; a dynamic algorithm for the Chinese Postman Problem. Done with industrial partner iEngineering.

Visual Question Answering

CLIP encoder + GPT-2 decoder architecture over the VQA dataset (265K+ images).

Multimodal Sentiment Analysis

RNNs for text (SENTIMENT140), CNNs for images (FER2013), and ASR for audio (LJSpeech-1.1) combined into one sentiment pipeline.

skills

languagesPython, Java, TypeScript, JavaScript, C, C++, SQL, HTML/CSS
machine learningRegression, classification, clustering, LLMs, CNNs, RNNs, transformers
automationn8n, Make.com, REST APIs, RAG pipelines, browser automation
toolsPyTorch, TensorFlow, Scikit-learn, Django, Flask, MERN, MySQL, MongoDB