Skip to content
View Hasebul's full-sized avatar

Highlights

  • Pro

Block or report Hasebul

Report abuse

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

Report abuse
Hasebul/README.md

Hi, I'm Md Hasebul Hasan πŸ‘‹

Ph.D. Researcher in Computer Science | NLP & LLMs | Agentic AI | LLM Systems | Machine Learning

I am a Ph.D. student and Graduate Research Assistant in Computer Science and Engineering at the University of Texas at Arlington (UTA).

My research focuses on Natural Language Processing, Large Language Models, Agentic AI, Human-AI Interaction, trustworthy AI, and efficient LLM systems. I am particularly interested in understanding when and why LLMs fail, developing methods to improve their reliability, and building efficient systems for real-world deployment.

Previously, I worked for 3+ years as a Machine Learning Engineer at IQVIA, where I developed production ML and LLM-based systems. I also served as a Part-Time Lecturer in the Department of Computer Science and Engineering at Bangladesh University of Engineering and Technology (BUET) from November 2022 to April 2024.

🎯 Currently seeking Research Internship opportunities in NLP, LLMs, Agentic AI, and LLM Systems/Architecture.


πŸ”¬ Research Highlights

  • 🌟 ICML 2025 Spotlight β€” Top 2.6%
    MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models

  • πŸ“˜ EACL 2026 Findings β€” First Author
    MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration

  • πŸ›‘οΈ COMPSAC 2024 β€” First Author
    GuardFL: Detection and Removal of Malicious Clients Through Majority Consensus

  • πŸ€– Working on research involving LLM evaluation, Agentic AI, trustworthy AI, efficient LLM inference, and KV-cache optimization


πŸ“š Publications & Research Projects

A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models

Developed a benchmark for evaluating the geospatial reasoning capabilities of foundation models.

A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration

A hierarchical agentic framework that dynamically integrates map tools for complex geospatial reasoning.

Detection and Removal of Malicious Clients Through Majority Consensus

A federated-learning defense mechanism for detecting and removing malicious clients.

A Multi-Modal Deep Learning Based Approach for House Price Prediction

A multimodal learning framework combining structured attributes, images, textual descriptions, and geospatial information.


πŸ’Ό Industry Experience

Machine Learning Engineer β€” IQVIA

May 2022 – July 2025

  • Developed and deployed LLM-powered applications using RAG and LangChain
  • Fine-tuned and deployed open-source language models
  • Built production machine-learning and forecasting pipelines
  • Worked with PyTorch, TensorFlow, Snowflake, AWS, Docker, Kubernetes, and Hugging Face
  • Collaborated with cross-functional teams to deploy scalable ML systems

πŸ† IQVIA Impact Program Awards

The IQVIA Impact Program is an internal employee-recognition program honoring exceptional performance, process improvement, and technical innovation across Platinum, Gold, Silver, and Bronze recognition levels.

  • πŸ₯‡ Platinum Award β€” 2024
  • πŸ₯ˆ Silver Award β€” 2025

πŸ‘¨β€πŸ« Teaching Experience

Lecturer β€” Department of CSE, BUET

November 2022 – April 2024

Served as a Part-Time Lecturer at the Bangladesh University of Engineering and Technology (BUET), where I:

  • Taught undergraduate Computer Science courses
  • Supervised student software and research projects
  • Mentored students in algorithms, databases, and software engineering
  • Designed and evaluated laboratory assignments and examinations

🧠 Research Interests

  • Natural Language Processing
  • Large Language Models
  • Agentic AI & Multi-Agent Systems
  • LLM Reasoning and Evaluation
  • Human-AI Interaction
  • Trustworthy & Reliable AI
  • Efficient LLM Inference
  • LLM Systems & Architecture
  • KV-Cache Optimization
  • Retrieval-Augmented Generation
  • Multimodal Machine Learning

πŸ› οΈ Technical Skills

Languages
Python C C++ Java JavaScript SQL LaTeX

AI / Machine Learning
PyTorch TensorFlow Hugging Face scikit-learn

LLM / Agentic AI
LLMs RAG LangChain Agentic AI Fine-Tuning Prompt Engineering

Cloud & ML Systems
AWS SageMaker AWS Bedrock EC2 ECR Docker Kubernetes

Databases
PostgreSQL MySQL MongoDB Snowflake

Development
Git FastAPI PyTest CI/CD


πŸŽ“ Education

Ph.D. in Computer Science and Engineering
University of Texas at Arlington
2025 – Present | GPA: 4.00/4.00

M.Sc. in Computer Science and Engineering
Bangladesh University of Engineering and Technology
2022 – 2025

B.Sc. in Computer Science and Engineering
Bangladesh University of Engineering and Technology
2017 – 2022


🌐 Connect With Me


πŸš€ Open to Research Internships

I am currently looking for Research Internship opportunities in:

NLP Β· Large Language Models Β· Agentic AI Β· LLM Systems Β· Efficient Inference Β· Human-AI Interaction Β· Trustworthy AI

If your team is working on any of these areas, I would be happy to connect.


⭐ Thanks for visiting my profile!

Popular repositories Loading

  1. MapAgent MapAgent Public

    Python 17 2

  2. solving15Puzzle solving15Puzzle Public

    This program solve 15 puzzle problem

  3. website.github.io website.github.io Public

    HTML

  4. ReactTutorial ReactTutorial Public

    Here I put all the files related to react development .

    HTML

  5. Hasebul Hasebul Public

    Config files for my GitHub profile.

    CSS

  6. webPage.github.io webPage.github.io Public

    HTML