AI Engineer
fiserv
Job Description
- Design and implement integrations with large language model application programming interfaces (APIs) such as Claude, GPT, Gemini, or similar model platforms.
- Build and support Model Context Protocol (MCP) integrations and related orchestration patterns that improve context handling and interoperability across AI-enabled applications.
- Develop agentic workflows and AI application frameworks using tools such as LangChain, LlamaIndex, CrewAI, or similar orchestration frameworks.
- Design, implement, and optimize retrieval-augmented generation (RAG) pipelines, including embeddings, vector stores, retrieval logic, and response grounding techniques.
- Build backend services and APIs using Python, asynchronous programming techniques, FastAPI, or similar frameworks to support scalable AI application delivery.
- Partner with product, engineering, and platform teams to translate business needs into technical AI solutions that are measurable, maintainable, and production-ready.
- Evaluate and improve application reliability, performance, observability, and security across AI workflows and integrated services.
- Support engineering productivity through modern development workflows and tools such as Cursor, Claude Code, or similar assisted development environments.
- Contribute to testing, validation, and continuous improvement of AI-enabled applications, ensuring solution quality and operational readiness.
- Responsibilities listed are not intended to be all-inclusive and may be modified as necessary.