Join ACES CØDE, a Microsoft engineering organization dedicated to enhancing the reliability and efficiency of the Microsoft Cloud. Our mission is to proactively address operational challenges, transforming customer and operational signals into lasting product improvements and AI-powered solutions.

We are seeking an Applied AI Engineer to develop the next generation of production agentic AI services. These services will accelerate customer issue resolution, reduce avoidable support demand, and elevate the scalability of AI-first support experiences. You will translate product specifications into robust, scalable AI services, leveraging LLM orchestration, multi-agent coordination, and RAG-based systems to directly impact Azure customers and empower their success on our cloud.

Microsoft fosters a culture of empowerment, innovation, and collaboration, guided by values of respect, integrity, and accountability. We strive to create an inclusive environment where everyone can thrive, building on our mission to empower every person and organization on the planet to achieve more.

Translate product requirements into detailed AI service architectures, breaking down business needs into agent workflows, data integrations, and scalable service designs.

Develop and implement agentic AI workflows using Azure AI Foundry Agent Service and Microsoft Agent Framework, focusing on multi-agent coordination and lifecycle management.

Build and refine LLM-based solutions, including prompt engineering, model selection, cost optimization, and RAG pipeline design.

Create robust evaluation systems with rubrics, golden datasets, and judge agents to ensure agent correctness and safety prior to production deployment.

Write production-quality C# and Python code using test-driven development, adhering to high standards for reliability, performance, and security.

Deploy services through CI/CD pipelines with feature flags and staged rollouts, ensuring comprehensive production observability (tracing, logging, metrics).

Implement secure service patterns such as RBAC, Managed Identities, and secrets management.

Integrate agents with Azure data sources and cloud-native services to ensure responses are grounded in real-time signals.

Apply Responsible AI practices throughout development, guaranteeing safe, fair, and compliant outputs.

Execute reliably within sprint commitments and collaborate effectively with ACES and partner engineering teams.

Manage the full lifecycle of AI service components, from design and development to testing, deployment, monitoring, and incident response.

Bachelor's degree in Computer Science, Engineering, or a related field is required.

Possess at least 3 years of software engineering experience in C# and/or Python, with proven experience deploying solutions to production.

Demonstrated experience in building or integrating with LLM-based systems, including prompt engineering, RAG, or agent frameworks.

Familiarity with key Azure services such as Azure OpenAI, Azure AI Foundry, Azure Functions, and Cosmos DB is essential.

Experience with CI/CD pipelines, automated testing methodologies, and production observability tools is necessary.

Solid understanding of fundamental data structures, algorithms, and system design principles is required.

Preferred qualifications include a Bachelor's or Master's degree in Computer Science or AI, experience with multi-agent orchestration, AI evaluation frameworks, RAG pipelines, container orchestration, microservices architecture, and cloud-native deployment patterns.