Data Scientist Specializing in Natural Language Processing

GitHub | LinkedIn | Kaggle
Email: [email protected] | Phone: +98-922-3896151

I am a Data Scientist with experience in Natural Language Processing (NLP) and Machine Learning, where I focus on building and deploying practical solutions. My primary strengths lie in NLP projects like ChatBots, Question Answering, and Summarization. In addition, I've explored various domains, including Computer Vision, Speech Processing, and Time-Series Analysis, gaining hands-on experience with tasks such as audio data collection, cryptocurrency prediction, and video action detection. While I am still growing my expertise in these fields, I continuously learn and improve through challenging projects.

M.Sc. in Computer Engineering - Artificial Intelligence and Robotics
Shahid Rajaee Teacher Training University (SRTTU), Tehran, Iran
Thesis: “Using Convolutional Neural Networks and Neural Graph Networks to Increase the Accuracy of Image Classification”
GPA: 17.05 / 20
Sep 2021 – Aug 2024

B.Sc. in Computer Engineering - Software
Imam Khomeini International University (IKIU), Qazvin, Iran
Thesis: “Cancer Detection Using Synchrotron Data and Machine Learning”
GPA: 15.80 / 20
Sep 2016 – Mar 2021

• Led the development of RAG-based and support system chatbots to enhance customer interactions.
• Optimized pipelines for GPU-efficient LLMs in low-resource environments, significantly improving performance and cost-efficiency.
• Designed and implemented Persian OCR for Document AI, enabling better document processing and extraction.
• Managed automated labeling tool data handling to streamline annotation workflows.
• Developed and deployed text summarization systems as part of a Document AI project, automating the summarization of organizational communication letters.

• Developed crawlers for 4000 hours of audio data collection, contributing to a large-scale speech processing project.
• Built a Persian TTS model, improving speech synthesis capabilities for the Persian language.
• Developed a Persian KenLM language model for improved text-based applications.
• Created a cryptocurrency prediction model and data crawlers, optimizing real-time predictions.
• Developed ASR and STT systems for noisy environments (25 SNR), enhancing transcription accuracy.
• Designed a desktop annotation tool to streamline labeling processes for large datasets.

• Worked on COVID-19 detection from blood test data, contributing to healthcare-related ML applications.
• Ranked as a Kaggle Notebook and Discussion Expert, sharing insights and solutions with the community.
• Developed STT and TTS systems for Persian, advancing the use of speech technologies in Persian.

• Contributed to computer vision studies, such as car palette and mask detection, enhancing visual recognition systems.
• Assisted in data gathering for machine learning, providing datasets for multiple ML models.
• Explored interpretable/explainable AI and developed a translation system for cross-lingual text applications.
• Created a poetry language model and worked on video action detection, expanding the range of NLP and CV applications.

• Data Science & Machine Learning: Machine Learning, Deep Learning, NLP, Knowledge Graphs, Graph Neural Networks, Computer Vision, Data Analysis, Visualization
• Libraries & Frameworks: Scikit-learn, Numpy, Pandas, Matplotlib, Seaborn, Plotly, PyTorch, Keras, Huggingface Transformers, LangChain, Ollama, Vllm, PaddlePaddle, PyTorch Geometric
• NLP & Chatbot Development: Rasa, Huggingface, LangChain
• Programming & Scripting: Python (Expert), Java, JavaScript, Node.js, SQL, HTML, CSS
• Web Development: Flask, FastAPI, Web Design
• Web Scraping: Scrapy, BeautifulSoup, Selenium, Requests
• Databases: MySQL, SQLite, Redis, ElasticSearch, Vector Databases
• DevOps & Tools: Git, GitHub, GitLab, Docker, Docker Orchestration, Kanban, LaTeX
• Software Development: Design Patterns, Test-Driven Development (TDD), Object-Oriented Programming (OOP), RESTful Services
• Operating Systems: Linux/Ubuntu, Windows