I am a Research Engineer with a keen interest in Natural Language Processing (NLP) and its applications, as well as in developing software tools for Data Science and Machine Learning.
- NLP: Exploring applications and advancing skills in natural language processing.
- Data Science & ML: Building models and deploying software tools for data science and machine learning projects.
- Applied ML: Applying machine learning techniques to diverse domains including genomics and infectious disease modeling.
- Programming Languages: Python, R, Bash
- ML Frameworks: TensorFlow, Keras, PyTorch
- Data Science Tools: scikit-learn, NumPy, pandas
- DevOps: Azure, Google Cloud, Docker, Terraform
- Full-stack Development: End-to-end machine learning web applications
- Geospatial: STAC, GeoJSON, raster data processing
-
Real-time Infectious Disease Risk System: Developing a real-time system for infectious disease risk assessment at LSHTM, working with statistical models to model count data for Lassa fever.
- Implementing a STAC (SpatioTemporal Asset Catalog) server for efficient management and distribution of climate data relevant to disease transmission.
- Developing API endpoints for serving processed climate indices and model predictions.
-
Transformer Model Fine-tuning: Implementing efficient fine-tuning of an MSATransformer using Low-Rank Adaptation (LoRA) for sequence modeling applications, focusing on computational efficiency for large models.
- Continually improving my NLP skills.
- Exploring efficient fine-tuning methods for large language models in specialized domains.
- Writing about the latest in ML research with a focus on NLP and general ML tooling on my blog.
- Email: [email protected]
🚧 Note: My blog is a work in progress, so stay tuned for updates!