Generative AI / AI Architect – AWS
Generative AI / AI Architect – AWS Currently USA-based and able to work EST hours - ONLY EST/CST candidates will be considered for remote Candidates outside the USA will be rejected regardless of technical score. Pennsylvania-based candidates willing to work hybrid will receive priority when technical qualifications are comparable. _____________________________________________
Job Description
We are seeking a highly experienced Generative AI / AI Architect to design, architect, and implement scalable, secure, and enterprise-grade AI solutions leveraging AWS cloud services, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI frameworks. The ideal candidate will bring strong hands-on expertise in Amazon Bedrock, Amazon SageMaker, Python, LangChain/LangGraph, vector databases, and enterprise AI integration, with a proven track record of delivering production-ready GenAI solutions. The architect will collaborate with enterprise architecture, engineering, cloud security, data engineering, and business teams to accelerate AI adoption across insurance and financial services operations.
Key Responsibilities
Lead end-to-end architecture and technical design of enterprise Generative AI solutions on AWS. Design and implement LLM-powered applications using Amazon Bedrock, Claude, Llama, and other suitable foundation models. Architect RAG pipelines incorporating document ingestion, embeddings, semantic search, vector databases, and response grounding. Build agentic AI solutions using LangChain, LangGraph, and appropriate orchestration frameworks. Develop secure integrations between GenAI applications and enterprise APIs, databases, document repositories, and existing applications. Design scalable AI architectures using AWS Lambda, API Gateway, S3, IAM, ECS/EKS, and relevant cloud services. Establish LLMOps/MLOps practices for model evaluation, observability, deployment, versioning, and operational monitoring. Implement AI guardrails, PII protection, encryption, access controls, and responsible AI governance. Optimize LLM latency, inference cost, throughput, reliability, and solution performance. Lead architecture reviews, proofs of concept, technical design discussions, and engineering implementation.