Our Fortune 15 healthcare client is seeking a highly skilled AI Engineer to lead the development and implementation of cutting-edge Generative AI solutions, with a focus on Retrieval-Augmented Generation (RAG). This role will play a critical part in designing and deploying intelligent applications that integrate custom embeddings, advanced chunking strategies, hybrid search, and structured outputs using varied large language models (LLMs). You’ll work at the intersection of machine learning, software engineering, and product innovation, building scalable solutions that enhance healthcare services through deep research capabilities, chatbot interfaces, sentiment analysis, topic modeling, and lead generation. Key Responsibilities • Lead product and development of a Generative AI application incorporating: RAG pipelines Form processing and generation Flow agent modeling and orchestration Topic modeling and lead generation Deep document research and sentiment analysis • Design and implement solutions using: Custom embeddings, chunking, prompting strategies Hybrid search combining vector and keyword-based techniques Structured output modeling using Pydantic classes • Work with multiple LLMs including OpenAI, Anthropic, and Llama • Architect and develop back-end services in Python • Integrate and manage data using PostgreSQL with VectorDB extensions and Full-Text Search (FTS) • Deploy and scale models and applications in cloud environments such as AWS • Collaborate cross-functionally with data scientists, ML engineers, and product managers Required Skills • Proven hands-on experience building and scaling RAG-based applications • Deep expertise in Chatbot Development, Natural Language Processing (NLP), and Prompt Engineering • Strong programming background in Python • Experience with PostgreSQL, including vector search and FTS • Familiarity with Pydantic, FastAPI, or similar frameworks for structured data output • Direct experience integrating LLMs such as OpenAI’s GPT, Anthropic’s Claude, or Meta’s Llama • Proficient in deploying AI/ML workloads in AWS or similar cloud environments • Strong communication and leadership skills for cross-functional collaboration Preferred Qualifications • Experience in the healthcare or regulated industries • Knowledge of LangChain, LlamaIndex, or other orchestration frameworks • Familiarity with vector databases (e.g., Weaviate, Pinecone) and embedding models • Exposure to form generation/processing tools and workflow automation