> Markdown version of [/jobs/ext/4769787-ai-fde-ai-architect](https://www.wearedevelopers.com/jobs/ext/4769787-ai-fde-ai-architect). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Ai Fde /Ai Architect - **Company:** Tata Consultancy Services Limited - **Location:** Minneapolis, MN, United States - **Salary:** $130,000 - $150,000 - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, ASC X12 Standards, Application Integration Architecture, Microsoft Azure, Cloud Computing, Cloud Engineering, Code Review, Continuous Integration, Information Engineering, Relational Databases, Software Debugging, JSON, Python (Programming Language), MongoDB, Node.Js, NoSQL, OAuth, Performance Tuning, Rapid Prototyping Process, JSON Web Token, Search Technologies, SQL Databases, Systems Integration, Unstructured Data, Extensible Markup Language (XML), Enterprise Search, Pinecone, Data Processing, Enterprise Software Applications, ReactJS, Fast Healthcare Interoperability Resources, Retrieval-Augmented Generation, Large Language Models, Prompt Engineering, Spring-boot, Generative AI, Backend, Fastapi, Pgvector, Information Technology, Cosmos DB, FAISS, Api Gateway, Restful APIs, Semantic Kernel, Data Pipelines, ChromaDB - **Published:** November 18, 2026 - **Apply:** https://diversityjobs.com/career/18959535/Ai-Fde-Ai-Architect-Minnesota-Minneapolis ## About the Role BACHELOR OF COMPUTER SCIENCE ## Description Must Have Technical/Functional Skills * Python hands-on development for APIs, automation, data processing, and AI applications. * Full-Stack Development: React.js preferred, with FastAPI, Node.js, or Spring Boot for backend services. * Generative AI / LLM Engineering: hands-on experience building and deploying enterprise LLM-based applications. * RAG & Vector Search: RAG architectures, embeddings, vector databases/search such as Pinecone, FAISS, ChromaDB, pgvector, or Azure AI Search. * AI Frameworks & Prompt Engineering: LangChain/Semantic Kernel, prompt engineering, structured outputs, and LLM API/model integration. * API & Integration Engineering: REST APIs, OAuth 2.0, JWT, API gateways, JSON/XML, and enterprise system integration. * Cloud-Native Engineering: hands-on experience with Azure, AWS, or GCP, including distributed and production-grade cloud applications. * Data Engineering: SQL/RDBMS, NoSQL such as MongoDB/Cosmos DB, data pipelines, and structured/unstructured data processing. * Healthcare/PBM Integration: NCPDP, X12 EDI (834/837/835), HL7 FHIR, and experience integrating healthcare/PBM systems. * AI Security & Production Engineering: HIPAA/PHI/PII controls, HITRUST/SOC 2 awareness, CI/CD, testing, monitoring, observability, performance, and production troubleshooting Roles & Responsibilities * Lead customer discovery and technical workshops to understand business problems, PBM workflows, existing systems, data, constraints, and success criteria. * Translate ambiguous customer requirements into scalable solution architectures, technical designs, and executable delivery plans. * Own the end-to-end technical delivery from rapid prototyping and PoC through engineering integration, testing, deployment, and production support. * Design and develop AI-enabled full-stack applications, including React-based experiences, Python/FastAPI services, REST APIs, and enterprise integrations. * Build and integrate GenAI/LLM solutions, including RAG, prompt engineering, embeddings, vector search, structured outputs, and agentic workflows. * Integrate solutions with healthcare and PBM platforms, supporting standards such as NCPDP, X12 EDI, HL7 FHIR, and enterprise data sources. * Ensure solutions meet security, privacy, scalability, reliability, and AI governance requirements, particularly for PHI/PII and HIPAA-aligned environments. * Remain hands-on with coding, code reviews, debugging, testing, performance optimization, and production troubleshooting. * Provide technical leadership and mentoring to engineers while establishing reusable engineering patterns, best practices, and quality standards. * Communicate architecture decisions, trade-offs, risks, progress, and measurable business outcomes clearly to engineering teams, customer stakeholders, and leadership.