• Develop AI‑powered applications using state‑of‑the‑art LLMs. • Build and deploy applications for internal customers, selecting the right models (e.g., GPT‑4o, Claude Sonnet 4, Gemini 2.5 or open‑source alternatives). • Implement retrieval‑augmented generation (RAG) pipelines and agents using LangChain, LangGraph, LlamaIndex, and other emerging frameworks. • Integrate ML models with front-end apps, REST APIs, and backend systems. • Design and build end-to-end AI systems, ranging from chatbots and recommendation engines to vision-based pipelines. • Build robust logic around ML models to address edge cases, failovers, and complex business rules. • Leverage prebuilt models or services (e.g., OpenAI API, Azure Cognitive Services, HuggingFace) to accelerate development cycles. • Fine‑tune and customize models using LoRA, prompt tuning, or RLHF techniques. • Occasionally perform custom model training, fine-tune or adapt existing models to meet business needs. • Work with vector databases (e.g., Pinecone, Weaviate) and explore graph-based approaches (e.g., GraphRAG, Knowledge Graphs). • Ensure privacy and compliance with HIPAA, including encryption, PHI protection, and vendor due diligence. • Prototype multi‑agent systems using frameworks like CrewAI or Stands SDK and evaluate emerging agent orchestration solutions. • Collaborate cross-functionally with product managers, data scientists, and compliance teams. • Mentor junior engineers, lead innovation discussions, and continuously evaluate emerging LLM architectures.