Download my Resume!
- Email : My middle name and first name, at gmail (My middle name - melesse, first name - bethel)
- Github - https://github.com/bethelmelesse
- LinkedIn - https://linkedin.com/in/bethelmelesse
Ajou University, Suwon, South Korea
- Overall GPA: 4.31/4.5
- Two-time TA for Digital Circuit and Database Course
Hankuk University of Foreign Studies, Seoul, South Korea
- Overall GPA: 3.75/4.5
- President of United Students of Silk-Road University Network
Addis Ababa Institute of Technology, Addis Ababa, Ethiopia
- #1 university in Ethiopia
- 3 semesters of undergraduate studies in Bachelor of Software Engineering
Database and Dependable Computing Lab
Ajou University, Suwon, South Korea
- Processed > 1000 TB of Common Crawl for < 2 $, extracting SOTA monolingual datasets for 7 languages.
- Improved multi-lingual LLMs using Quantized Low-Rank Adaptation (QLoRA) on consumer GPUs.
- Published in Proceedings of Symposium of the Korean Institute of Communications and Information Sciences.
- Code released at “UnifiedCrawl”
- Improved cross-domain/cross-task generalization of multi-modal classifiers by fusing descriptions of classes/tasks.
- Achieved SOTA zero-shot performance on CIFAR, RCV1, 20 NG (under review for publication).
- Trained a BERT-like transformer Language-Model (LM) for IR for African languages.
- Compared traditional IR approaches (tf-idf, BM25) vs. SOTA approaches.
- Added support for more languages to “AllTrans”, an android application translator.
- Added extra languages to “Android-Auto-Localization”, to localize Android application’s resources.
| Programming Languages | Python (Intermediate), Java (Intermediate), Shell Script (Beginner) |
| Machine Learning | Deep Neural Networks, Generative Models |
| Deep Learning Libraries | Pytorch, HuggingFace, Pandas, NumPy, Scikit-learn, SciPy |
| Mathematics & Statistics | Linear Algebra, Probability Theory, Hypothesis & Significance Testing |
| Typesetting & Version Control | Latex (Advanced), Git/Github (Intermediate) |
| Natural Language Processing(NLP) | Transformers(BERT, GPT, LLaMa), Large Language Modeling, Prompt Engineering, Question Answering |
| Computer Vision(CV) | Convolutional Neural Networks (CNNs), Object Detection and Recognition, CLIP, ViT, ResNet Models |
| English | 915/990 (Professional) in TOEIC English Reading and Listening (2021) |
| Korean | 1-year Intensive Korean Language Course (2017-2018) |
| Korean | TOPIK Level 4 (2021) |
Advanced Artificial Intelligence, Advanced Machine Learning, Advanced Topics in Machine Learning (GNN), Advanced Computer Vision, Introduction to Natural Language Processing, Information Retrieval, Advanced Image Signal Processing, Industrial Mathematics Survey.
| Natural Language Processing Models | Transformer Model, Bert Model, GLUE, ORQA |
| Computer Vision Models | CLIP Model, ViT Model, ResNet Model |
| Other ML Models | EGT Model |
| Academic Scholarship | Ajou Research Scholarship (2023) - Recommended by HOD as Excellent Student, |
| BK Research Scholarship(2022-2024), Ajou Tuition Scholarship (2022-2024) | |
| HUFS Tuition Scholarship (2017-2022), Exemplary Student Award (2017) | |
| Korean War Scholarship | Awarded by the Embassy of Republic of Korea(2026), Korean War and Military |
| Police Widow's Association (2020), Korean War Memorial Foundation (2017-2022), | |
| Memorial Association of UN Participation in Korean War (UNPK) (2023) | |
| Certificates | KAIST-AAiT IT Training Course (2016), Intensive Korean Language |
| Course, HUFS (2017-2018) |
Volunteering for NGOs (Korean Saemul Undong Center, The Korea-Africa Foundation Festival, etc.), acting as Translator/Interpreter/tour guide at the Korean War Veterans Revisit Program, Barista at Hwacheon Ice Festival