My skills

• 

  Generative AI with RAG and LLM

  - Develop Retrieval-Augmented Generation (RAG) pipelines that combine vector databases and LLMs to deliver context-aware, domain-specific answers.
  - Fine-tune Large Language Models (LLMs) and optimize prompt engineering to improve accuracy, reduce token usage, and enhance generation quality.
  - Integrate open-source LLMs (e.g., LLaMA 2, Mistral) or API-based models (e.g., GPT-4o) into applications for conversational AI, document Q&A, and knowledge assistants.

• 

  Machine Learning

  - Utilize predictive modeling techniques to identify patterns for data-driven decisions using Python Scikit-learn
  
  - Classification: Logistic regression, K-nearest neighbors, Decision Tree, Random Forest, Gradient Boosting Regression Trees
  
  - Quantitative: Linear regression
  
  - Unsupervised: K Means clustering
  
  - Time series: Long short-term memory, ARIMA

• 

  Data collection

  - Utilize APIs to collect and aggregate data for analysis.
  
  - Perform web scraping with Python BeautifulSoup and Selenium WebDriver to gather information

• 

  Data wrangling

  - Clean and organize raw data with Python Pandas and Numpy, ensuring high-quality datasets for analysis.
  
  - Utilize SciPy for solving linear equations & statistical analysis to preprocess complex datasets.

• 

  Database management

  - Manage and maintain databases using MySQL, PostgreSQL, or MongoDB (NoSQL)
  
  - Design databases with Entity-relationship Diagrams (ERDs) & logical modeling
  
  - Migrate from on-premises / local data centers to the Cloud with AWS, Microsoft Azure or Google Cloud

• 

  Data Visualization

  - Create visualizations with Python Matplotlib and Seaborn
  
  - Develop interactive dashboards with Tableau & Power BI to effectively communicate insights.