Machine Learning Engineer
•Developed and fine-tuned Retriever Augmented Generation (RAG) models using the LangChain framework, integrating retrieval techniques with generative models to enhance content generation. This work involved optimizing retrieval strategies and model architecture to create highly relevant, context-aware outputs in a variety of use cases.•Implemented RAG Fusion and multi-query techniques to boost the accuracy and relevance of the generated content. These techniques allowed for a more comprehensive and nuanced retrieval process, leading to better alignment between queries and results.•Developed a custom program to measure the accuracy of RAG models, implementing various metrics to evaluate performance and optimize model effectiveness. This helped in fine-tuning model parameters and provided actionable insights for continuous improvement.•Scraped data using APIs to gather and preprocess large datasets, ensuring high-quality input data for model training and evaluation. Employed advanced data cleaning techniques and feature engineering to prepare the data for downstream machine learning tasks, enhancing the overall performance of the RAG models.
