About

We are looking for a highly skilled Machine Learning Engineer with deep expertise in Natural Language Processing (NLP) and Large Language Model (LLM) development. The ideal candidate will be responsible for building a secure, private, company-specific LLM with full retrieval capabilities. You will work with company documents, PDFs, transcripts, e-books, policies, and other internal data to create a robust Retrieval-Augmented Generation (RAG) system. Responsibilities Develop a fully customized LLM tailored to company and client needs Build a secure, private environment for the model and data Implement a complete RAG pipeline using internal documents and knowledge bases Optimize the LLM for high performance, accuracy, and reliable outputs Work closely with the team to integrate the model into internal workflows and tools Ensure data privacy, compliance, and efficient deployment Deliverables A custom LLM trained on company/client data A secure and fully private client-based setup A high-performance RAG system using internal content Optimizations for accuracy, speed, and scalability Preferred Qualifications Proven experience in LLM fine-tuning or building models from scratch Strong background in NLP, deep learning, and vector databases Experience with RAG frameworks, embeddings, and document preprocessing Familiarity with secure ML deployment (on-premise or private cloud)