We are looking for a results-oriented AI Engineer to join our team developing intelligent Q&A systems powered by large language models. You will help build, test, and optimize pipelines that enable automatic question-answering from large document collections, supporting our mission to surface key knowledge rapidly and accurately.ResponsibilitiesBuild, fine-tune, and evaluate LLM-based Q&A models using frameworks like AWS Bedrock, Langchain, HuggingFace Transformers or OpenAI API.Design prompt templates and implement retrieval strategies to increase answer precision and factuality.Assist in creating data pipelines for training and testing, including annotation and evaluation tooling.Collaborate with senior engineers and product managers to translate user requirements into technical features.Participate in error analysis, iterative model improvement, and performance tuning.Document code and workflows clearly; follow best practices for reproducibility and code quality.RequirementsHands-on experience with machine learning, NLP, or information retrieval projects, preferably with language models.Proficiency in Python and familiarity with deep learning / NLP libraries (Langchain, PyTorch, TensorFlow, HuggingFace Transformers).Knowledge of v... #J-18808-Ljbffr