AI Staff Engineer

Staff Applied AI EngineerPosition Summary: Our partner, a nationally recognized healthcare organization, is bringing long-term ownership of its applied AI platform in-house. They are hiring a Staff Applied AI Engineer to become the technical authority for production AI systems while remaining deeply hands-on with Python development, AI architecture, evaluation, deployment, and production operations.This role extends far beyond building prompts or integrating LLM APIs. You'll design and evolve multi-agent AI systems, make critical architectural decisions, establish evaluation and testing strategies, and determine when AI is the right solution versus when traditional software should be used. The platform supports real patient interactions where reliability, safety, and engineering judgment directly influence the user experience.This is an opportunity for an experienced software engineer who enjoys solving complex engineering problems, building production AI systems, and taking long-term ownership of a rapidly evolving platform.Experience and Education:• B.S. in Computer Science, Software Engineering, or a related technical field, or equivalent professional experience• Staff-level or highly senior software engineering background with ownership of production AI applications used by real customers• Expert-level Python development experience building scalable backend applications• Proven experience designing multi-agent AI systems, agent orchestration, or complex LLM-powered workflows• Hands-on experience building AI evaluation frameworks, regression testing, guardrails, and observability for production AI• Experience designing cloud-native backend systems and integrating AI into production applications• Experience working within healthcare or other regulated industries is preferred but not required Skills and Strengths: • Python• Applied AI• Agent Orchestration• Multi-agent Systems• LLM Orchestration• LangGraph• LangChain• AI Evaluation• Prompt Regression Testing• FastAPI• Pydantic• AsyncIO• AWS Bedrock• Prompt Injection Testing• Hallucination Mitigation• Retrieval-Augmented Generation• Vector Search• API Design• AI Observability• AI Guardrails Primary Job Responsibilities: • Take long-term technical ownership of the organization's applied AI platform and production architecture• Learn the existing AI platform from the external engineering team and transition ownership in-house• Design, build, test, deploy, and operate production AI applications using Python and modern cloud services• Architect multi-agent workflows involving routing, tool calling, context management, asynchronous processing, and human escalation• Determine when AI, deterministic software, or existing workflows are the appropriate solution for a given problem• Build AI evaluation frameworks, regression testing strategies, and repeatable validation processes• Investigate hallucinations, latency issues, inconsistent responses, and other production AI failures• Improve AI accuracy while balancing performance, cost, reliability, security, and user experience• Develop guardrails, human escalation paths, and failure-handling strategies for patient-facing AI experiences• Design scalable backend services, APIs, and integrations that support AI-powered applications• Establish observability, monitoring, and operational standards for production AI systems• Partner with product, engineering, executive, and clinical stakeholders to shape AI capabilities that solve real business problems• Evaluate architectural tradeoffs and recommend practical, production-ready AI solutions• Help establish the engineering standards and technical foundation for future AI initiatives across the organization