Embedded Files
Bethelhem Mebratu
Addis Ababa, Ethiopia
Addis Ababa University (2015-2020)
BSc. (Electrical and Computere Engineering)
BSc. (Electrical and Computere Engineering)
Email: bethelhem.mebratu.123@gmail.com
Programming tools
Programming tools
numpy
pandas
Scikit-learn
Matplotlib
Seaborn
Apache Kafka
Apache Airflow
Pytorch
Tensorflow
Data Engineering
Data Engineering
SQL
DBT
Power BI
Machine Learning
Machine Learning
EDA
MLflow
Generative AI
Generative AI
Langchain
LLMs
Prompt Engineering
Fine-tuning
RAG
About me
A junior Generative AI Engineer with a programming foundation and committed to advancing my skills in AI and technology . My expertise lies in Python, SQL and vector databases. I have hands on experience in building and fine-tuning Generative AI models, LLMs implementing RAG systems, and developing chatbots. Additionally, I am skilled in various data-related tasks such as analysis, processing, visualization, and building data warehouses.
Education
- 10 Academy ( April 2024-July 2024 )
Generative AI,Machine Learning and Data Engineering
Generative AI,Machine Learning and Data Engineering
GitHub
Business objective and understanding
Exploratory data analysis
Data Warehouse design and maintenance
MLOps,
CI/CD
Natural Language Processing (NLP)
Prompt Engineering
Large Language Models (LLMs)
FineTuning.
Retrieval Augmented Generation
Education
- Addis Ababa University (Addis Ababa Institute Of Technology) ( 2015-2020 )
BSc.(Electrical And Computer Engineering)
BSc.(Electrical And Computer Engineering)
Probability and Statistics
Object Oriented Programming
Computer Architecture
Interface
Robotics
Work Experience
- Junior Generative AI, Machine Learning and Data Engineer
10 Academy (April 2024 - Present)
10 Academy (April 2024 - Present)
I designed project workflows to streamline processes and enhance efficiency, ensuring smooth project execution. I worked on
machine learning projects to develop and implement advanced algorithms , driving innovation and achieving project goals.
Additionally, I fine-tuned large language models to improve their performance , enhancing their accuracy and capabilities.
I improved models using Retrieval-Augmented Generation (RAG) techniques to boost their effectiveness , providing valuable
insights and solutions.
Work Experience
- Electrical lighting engineer
JEME (April 2021- June 2024)
JEME (April 2021- June 2024)
I designed lighting systems for residential, apartment, and mixed-purpose buildings to meet clients' specific needs and preferences
using Autocad. I collaborated closely with team members of three or more people to identify and solve complex issues, ensuring
seamless project execution. Additionally, I actively engaged with customers to understand their requirements and developed
tailored lighting solutions that exceeded their expectations. I utilized design models and report templates to understand and
create reports , ensuring accuracy and clarity in project documentation. I was also responsible for designing electrical lighting
systems and managing projects , ensuring timely and successful completion .
Projects
Automated Storyboard Synthesis for digital Advertising:Semantic Image and Text Alignment
Automated Storyboard Synthesis for digital Advertising:Semantic Image and Text Alignment
Automating an end-to-end process of advertising production to significantly expedite the ideation and execution phases. This automation enables clients to swiftly launch their campaigns with minimal time and resource expenditure. A key component involves generating potential creative concepts based on the client's brief, ensuring tailored and effective campaign strategies.
Scalable Backtesting Infrastructure
Utilizing LLM (Language Model) forecasting to simulate and analyze current and historical financial market situations. While acknowledging that past performance doesn't guarantee future outcomes, conducting backtests helps understand trends and patterns over time. The focus lies on gaining a comprehensive understanding of the financial system and stock market trading.
Precision RAG:prompt tuning for building enterprise grade rag systems
Precision RAG:prompt tuning for building enterprise grade rag systems
This project focuses on fine-tuning large language models (LLMs) to improve embedding quality and text generation capabilities. The goal is to create models that better understand and generate text in these languages, which are underrepresented in current NLP research. This repository tries to build enterprise-grade Retrieval-Augmented Generation (RAG) system.
Redash Chatbot LLM
Redash Chatbot LLM
The Redash Chatbot LLM is an innovative integration that brings the power of OpenAI's ChatGPT model to your Redash dashboard. This integration allows users to interact with their Redash dashboards using natural language queries, making data exploration and analysis more intuitive and user-friendly. The Redash Chatbot LLM plugin provides conversational query capabilities, automated data visualization, and seamless integration with Redash.
Page updated
Google Sites
Report abuse