Machine Learning Engineer
CurrentIntegrating embedding models to generate text embeddings fromresearch publications and other text based sources to implement RAG within LLM chat applications.Designing and implementing the data processing pipeline to handle the conversion of millions of PDF, XML and other files into a suitable format for text embedding.Setting up and maintain the vector database infrastructure, ensuring efficient storage and retrieval of embeddings.Developing and maintaining the API for semantic search, allowing for robust querying capabilities.Collaborating with stakeholders to gather requirementsand ensure the system meets the needs of the organization.Conducting testing and quality assurance to ensure thereliability and accuracy of the search results.Documenting the system architecture, API usage, and operational procedures for future reference and maintenance.