I have a strong foundation in linear algebra, calculus, and probability theory, which provides me with a deep understanding of the mathematical principles underpinning machine learning. In terms of practical skills, I am proficient in training, testing, and validating models, as well as performing hyperparameter tuning and interpreting metrics and loss functions. I am also skilled in using PyTorch and Hugging Face for model development.
My expertise lies in working with text data. I have developed scalable PySpark workflows to preprocess large-scale text datasets, ensuring efficient and reliable data pipelines for high-demand Natural Language Processing (NLP) operations in production environments.
In addition, I have significant experience in computing dense representations from text data, focusing on optimizing embeddings such as Word2Vec, GloVe, and contextual models for applications like similarity search, document clustering, and information retrieval.