About Me

A passionate ML & NLP engineer with expertise in web development and a focus on under-resourced languages.

I am a Machine Learning and Natural Language Processing enthusiast with a strong background in web development. I completed my Master's in Computer Science (Informatics) at the Technical University of Munich, focusing on Deep Learning and NLP.

My research interests include language modeling for under-resourced languages, personality trait estimation, and applying machine learning to solve real-world problems. I have experience working with various machine learning frameworks. Furthermore, I have published papers in international conferences.

Currently based in Freising, Germany, I am passionate about developing innovative solutions that bridge the gap between technology and linguistics.

Abdullah Al Sefat

Skills & Expertise

My technical toolkit and areas of expertise

Programming Languages

  • Python
  • SQL
  • PHP
  • HTML/CSS
  • C++
  • Java
  • C#
  • R

Machine Learning

  • Classical ML Models
  • Deep Learning Architectures
  • Transformers
  • Fine-Tuning
  • Hyperparameter Tuning
  • Natural Language Processing
  • Large Language Models
  • Prompt Engineering
  • Retrieval Augmented Generation

Libraries & Frameworks

  • LangChain
  • ChromaDB
  • NumPy
  • Pandas
  • PyTorch
  • Scikit-Learn
  • Hugging Face
  • FastText
  • Spacy

Tools & Platforms

  • Git
  • Docker
  • CI/CD
  • JIRA
  • Slack
  • Teams
  • Miro

Languages

  • Bengali (Native/Bilingual)
  • English (Native/Bilingual)
  • Hindi (Intermediate)
  • German (Pre-Intermediate)

Experience & Education

My academic and professional journey

Software Developer

Aug 2022 - Present

Koinon - TU Munich

  • Full-stack web development in PHP
  • Implementing new features, testing, and solving bugs in an Agile Sprint environment
  • Developed for the Koinon school portal

Master's Thesis

Apr 2024 - Dec 2024

Schütze Lab, Institute for Information and Language Processing, LMU

  • Developed a web lookup system to collect and analyze text for under-resourced languages
  • Applied language modeling techniques and perplexity analysis to assess text quality
  • Built a dataset pipeline for low-resource NLP research

Interdisciplinary Project

Sep 2023 - Dec 2023

Technical University of Munich – School of Management

  • Conducted research on estimating the OCEAN personality traits of startup founders using social media data
  • Investigated the correlation between personality traits and entrepreneurial success

MSc. in Informatics

Oct 2021 - Dec 2024

Technical University of Munich

  • Focus on Deep Learning and Natural Language Processing

Bachelor's Thesis

Oct 2017 - Oct 2018

CSE Department, Ahsanullah University of Science and Technology

  • Developed a machine learning pipeline for rice yield prediction using multispectral satellite images
  • Processed and analyzed MODIS imagery to estimate crop yields
  • Applied regression models and remote sensing techniques

BSc. in Computer Science and Engineering

Oct 2014 - Dec 2018

Ahsanullah University of Science and Technology

  • Focus on Software Development and Computer Networks

Projects

A selection of my research and development work

GlotWeb and GlotSparse

Creating Corpora in Under-Resourced Languages

Developed an automatic pipeline to crawl the web for links in under-resourced languages and built a textual dataset for language modeling and perplexity analysis.

NLP Web Crawling Language Modeling
LangChain

LLM powered Pokédex

A Python application that leverages multimodal LLM to identify Pokémon from webcam images and retrieve detailed information about them.

LLMs Computer Vision Prompt Engineering
RoboAdvisor

University Chatbot Prototype

Developed a prototype RAG chatbot leveragin OpenAI for university administration that provides user support based on question regarding user portal.

Chatbots LLM Retrieval Augmented Generation
ChatGPT Legal Documents

Can ChatGPT structure Indian Legal Documents?

Evaluated zero-shot performance of GPT 3.5 and 4 for legal sentence labeling using OpenAI's API.

LLMs Legal NLP Zero-shot Learning
OCEAN Personality Traits

OCEAN Personality Trait Estimation

Developed a crawling agent leveraging Selenium and Beautiful Soup to curate social media texts. Scraped and analyzed social media content of 6,000 startup founders to estimate their OCEAN personality traits and explored the relationship with startup success.

Psycholinguistics Social Media Analysis Data Analytics
Sentence Classification

Finetuning Transformers and Sequential Models for Sentence Classification

Compared various deep learning approaches (BiLSTM-CRF, T5, Seq2Seq, LegalBERT) for rhetorical role labeling in Indian legal documents.

Transformers Deep Learning Legal NLP
Rice Yield Estimation

Rice Yield Estimation from Multispectral Images

Reprojected NDVI images from NASA's satellites to estimate rice yield using ML algorithms. Published at IEEE IGARSS 2019, Yokohama, Japan.

Remote Sensing Agriculture Machine Learning

Publications

My research contributions to the scientific community

Boro Rice Yield Estimation Model Using Modis NDVI Data for Bangladesh

DOI: 10.1109/IGARSS.2019.8899084

Published at IEEE IGARSS 2019, Yokohama, Japan

Citations: 15

Mobile Based MCQ Answer Sheet Analysis and Evaluation Application

DOI: 10.1109/SMART46866.2019.9117468

Citations: 9

Question Answering System over Linked Data: A Detailed Survey

DOI: 10.18034/ra.v8i1.449

Citations: 3

Contact Me

Let's connect and discuss potential collaborations

Get In Touch

Email: in.sefat@tum.de

Phone: +49 157 5289 4251

Location: Freising, Germany

Send a Message