Principal Applied Scientist, Agent Observability (CoreAI)
 Microsoft | |
 United States, Washington, Redmond | |
 Oct 01, 2025 | |
|
OverviewThe Foundry Agent Platform organization within Azure AI Platform is at the forefront of building the next generation of AI-driven solutions that power Microsoft's most innovative products and services. Our work underpins key Azure AI offerings, enabling intelligent, scalable, and reliable AI experiences across the Microsoft ecosystem. Within Foundry Agent Platform, the Agent Observability team is focused on developing advanced tools and platforms to monitor, evaluate, optimize and self-improve AI agent performance. We are seeking a passionate and skilled Applied Scientist to join the Agent Observability R&D team to help integrate the latest science innovations into the Foundry Agent Platform. In this role, you will: Understand latest scientific advancements and collaborate with leading researchers to incubate cutting-edge RL techniques into the Foundry Agent Platform Push the envelope on agent evaluation and experimentation, advancing the state-of-the-art by connecting customer needs, latest science techniques and product opportunities Collaborate closely with backend engineers, data scientists, site reliability engineers (SREs), and product managers to gather requirements, iterate on features, and deliver seamless, end-to-end user experiences. Collaborate closely with designers, UI-experts and engineers to ensure clear, actionable dashboards and visualizations that empower users to make trustworthy science-informed decisions. We are looking for candidates who are passionate about translating AI research into customer impact, with a deep understanding of observability and monitoring principles. If you thrive in collaborative environments and are excited to shape the future of AI agent observability and evaluation, we'd love to hear from you!
ResponsibilitiesHelp to shape the direction of Agent Foundry Platform and Agent self-improvement with industry-leading product work Collaborate with and bridge the gaps between researchers (e.g., across CoreAI, Microsoft Research [MSR] and open source communities) to translate applied research into differentiated, production-quality features Bring new technology and approaches, such as Reinforcement Learning from Human Feedback (RLHF), into production by applying long-term research efforts to drive Agent self-improvement Drive negotiations across teams to ensure cutting edge technology is being applied to products in a practical way that meets key business objectives Leverage and/or construct data and experimentation to rapidly iterate on and refine product opportunities in a rapidly evolving domain Proactively provide mentorship and coaching to less experienced and mid-level team members by sharing expertise to build team capabilities and guiding team members in projects, and their careers | |