Applied AI Engineer II

Translate product specifications into AI service architectures — decompose business intent into agent workflows, data source integrations, and scalable service designs. and agent lifecycle management. Develop and iterate on LLM-based solutions including prompt engineering, model selection, cost/token optimization, and RAG pipeline design. Build evaluation systems including rubrics, golden datasets, and judge agents to validate agent correctness and safety before production deployment. Write production-quality C# and Python with test-driven development, ensuring services meet reliability, performance, and security standards. Deploy services using CI/CD pipelines, feature flags, and staged rollouts with full production observability (tracing, logging, metrics). Implement secure service patterns including RBAC, Managed Identities, and secrets management. Integrate agents with Azure data sources and cloud-native services to ground agent responses in real-time signals. Apply Responsible AI practices across all agent development, ensuring outputs are safe, fair, and compliant. Execute reliably within sprint and co-development commitments across ACES and partner engineering teams. Own the end-to-end lifecycle of AI service components, including design, development, testing, deployment, monitoring, and incident response. Bachelor's Degree AND 2+ years experience in low-code application development, engineering product/technical program management, data analysis, or product development OR equivalent experience. Bachelor's Degree AND 5+ years experience in low-code application development, engineering product/technical program management, data analysis, or product development OR equivalent experience. 1+ year(s) of experience using low-code/no-code platforms (e.g., Dataverse, Power Applications). 1+ year(s) of experience managing and configuring artificial intelligence solutions (e.g., chatbots). 1+ year(s) of experience with programming/coding. Experience with CI/CD pipelines, automated testing, and production observability.