Full Stack Generative AI Engineer
Yogesh KumarUnited StatesMIDPosted 8h ago
PythonReact.jsFastAPIFlaskGenerative AILLMsPrompt EngineeringRAGLangChainLangGraphAgentic AIAzure OpenAIOpenAI APIsVector DatabasesEmbeddingsSemantic SearchREST APIsDockerKubernetesCI/CDCloud deploymentsHIPAAPHIHL7FHIR
About the Role
We are seeking an experienced Full Stack Generative AI Engineer to join our team for a prestigious customer, Optum. This is a remote contract position based in the USA, focused on building and deploying generative AI applications.
Key Responsibilities
• Develop full stack applications using Python and React.js
• Build backend services with FastAPI or Flask
• Implement generative AI solutions leveraging LLMs and prompt engineering
• Design and build RAG (Retrieval-Augmented Generation) applications
• Work with LangChain, LangGraph, and Agentic AI frameworks
• Integrate Azure OpenAI or OpenAI APIs
• Utilize vector databases, embeddings, and semantic search
• Develop REST APIs and enterprise integrations
• Deploy and monitor production-grade AI applications using Docker, Kubernetes, CI/CD, and cloud platforms
Requirements
• Strong hands-on experience with Python and React.js
• Backend development experience with FastAPI or Flask
• Solid understanding of Generative AI, LLMs, and Prompt Engineering
• Experience building RAG applications
• Proficiency with LangChain, LangGraph, and Agentic AI frameworks
• Experience with Azure OpenAI or OpenAI APIs
• Knowledge of vector databases, embeddings, and semantic search
• Experience developing REST APIs and enterprise integrations
• Familiarity with Docker, Kubernetes, CI/CD, and cloud deployments
• Preferred: Healthcare or Healthcare Payer domain experience
• Preferred: Knowledge of HIPAA, PHI, and healthcare data security
• Preferred: Exposure to HL7/FHIR standards
• Preferred: Experience deploying and monitoring production-grade AI applications
• Work Authorization: Only Visa Independent Candidates (USC, GC, GC-EAD)