About Me
I am an Astronomy PhD Candidate at the University of Cape Town and the South African Astronomical Observatory, researching active radio-emitting stars using multi-wavelength data from MeerKAT, Gaia, and eROSITA. My work involves cross-matching millions of astronomical sources, optical spectroscopy, and statistical analysis to understand stellar magnetic activity.
Alongside my research, I build machine learning systems, LLM applications, and data engineering pipelines. I have developed RAG-based chatbots, computer vision classifiers, fraud detection models, and fine-tuned large language models. I combine scientific rigor with practical engineering to solve real-world problems with AI.
About The Blog
This blog serves as a platform to share technical insights, tutorials, and discussions related to astronomy, scientific computing, machine learning, and data engineering. Here, you will find write-ups on deep learning techniques, large language model fine-tuning (LoRA), and data engineering best practices.
My Skills and Experiences
My core programming stack centers around Python, R, SQL, Bash, and Git. In machine learning, I actively use PyTorch, Scikit-learn, XGBoost, and Hugging Face, alongside LLM tools like LangChain, LiteLLM, and Pinecone. I also build data pipelines using BigQuery, Postgres, dbt, Apache Airflow, and Prefect, leveraging cloud platforms (AWS, GCP) for deployment.
Research and Projects
In addition to academic astronomy research (catalog cross-matching and radio discovery pipelines), I work on diverse data science projects. These include medical speech transcription using Whisper, image classification for brain tumors, weather-based disease prediction, and multi-agent retrieval-augmented generation systems.