Microsoft's Commerce Risk Analytics team is seeking AI Agent leaders to develop intelligent multi-agent systems that address challenges in fraud prevention and customer support automation by leveraging large language models (LLMs) and applied machine learning.
Requirements
- 3+ years of experience in Python for development and scripting.
- 2+ years of experience with LLMs, prompt engineering, and the OpenAI API.
- Experience working with multi-agent frameworks such as AutoGen, Semantic Kernal and Langchain.
- Experience with Azure services, cloud infrastructure, and CI/CD pipelines.
- Knowledge of MLOps practices, including containerization, infrastructure-as-code, and monitoring.
- Exposure to Power Platform, Microsoft Graph API, or enterprise integration technologies
Responsibilities
- Design, build, and iterate on AI agents leveraging LLM models, multi-agent frameworks, and Microsoft’s AI ecosystem
- Develop infrastructure and MLOps pipelines to support continuous training, deployment, and monitoring
- Conduct rigorous behavior testing and validation, focusing on performance, safety, and real-world edge cases
- Integrate AI agents with Azure AI services, Microsoft Graph API, Power Platform, and internal systems
- Apply best practices in security, compliance, and privacy to all aspects of agent development
- Document agent behavior, test results, and learnings to ensure transparency and knowledge sharing
Other
- Ability to meet Microsoft, customer and/or government security screening requirements are required for this role.
- Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud Background Check upon hire/transfer and every two years thereafter.
