• Propose, plan, and execute applied research initiatives that will make a real-world impact on Conversational AI using Large Language Models (LLMs) within a commercial setting. • Use expert knowledge of Transformer architecture mechanics (Attention, Tokenization, Embeddings) to consistently find the most effective, efficient, stable, explainable, and elegant prompting and orchestration approaches. • Utilize modern LLM inference and retrieval pipelines. • Analyze large scale conversational datasets for RAG (Retrieval-Augmented Generation) optimization. • Bring research-inspired prompt strategies to life within production systems. • Create durable, flexible scientific evaluation and experimentation capabilities for non-deterministic model outputs. • Present findings on model behavior and context efficacy in ways that inform and guide business and product strategy. • Work closely with other scientists. • Stay current with the rapidly evolving state of Generative AI.