Responsibilities: Design how AI models plug into our core systems and applications Integrate LLMs and AI frameworks using tools like LangChain or Semantic Kernel Build RAG pipelines and work with vector databases where needed Set up APIs and microservices to connect AI into the broader tech stack Evaluate AI platforms for cost, performance, and compliance fit Handle data privacy, model risk, and monitoring for anything in production Work closely with data science, engineering, and infrastructure teams. Requirements: 8+ years in application/solution architecture, 3+ in AI/ML integration Hands on experience with LangChain, Hugging Face, TensorFlow, or similar Experience with LLM platforms: OpenAI, Anthropic, Azure OpenAI, AWS Bedrock Strong grasp of RAG, vector databases (Pinecone, Weaviate, FAISS) Solid background in APIs, microservices, event driven architecture Comfortable in AWS, Strong coding skills in Python, Java Understanding of MLOps/LLMOps.