Principal Applied Scientist

Copilot Connectors Service transforms enterprise knowledge from systems such as ServiceNow, Salesforce, Azure DevOps, Jira, Confluence GitHub, and other business-critical applications into first-class knowledge within the Microsoft ecosystem. This knowledge powers Microsoft 365 Copilot, Cowork, Autopilot, WorkIQ, GitHub CLI, and future AI experiences by making external content, permissions, relationships, and business context available as trusted, AI-ready enterprise knowledge. This allows customers to manage knowledge and automations that cuts across many system of records and workflow system right in Microsoft Copilot. Copilot Connectors team works across the stack, from crawl systems, data modelling, information extraction, indexing, query and retrieval, integrations into different hardness system, writing skills and plug-ins and hill climbing by building Eval systems.  We manage a large footprint of connectors and our building set of agents which help us manage and scale the Connectors ecosystem. As a Principal Applied Scientist, you will work closely with leadership to define the scientific foundations for enterprise retrieval, grounding, evaluation, and agent-ready knowledge systems and automations that power the next generation of Microsoft AI experiences.

Drive innovation in enterprise retrieval,, ranking, grounding, and knowledge representation and autonomous workflows for AI agents and next-generation Microsoft AI experiences. Advance retrieval quality science through SEVALs, evaluation frameworks, and metrics for Recall@K, grounding quality, citation correctness, freshness, coverage, and task success. Develop techniques for multi-hop retrieval, cross-source reasoning, semantic enrichment, knowledge graphs, and agent memory. Build trust-aware AI systems that respect enterprise permissions, provenance, and authorization. Pioneer autonomous knowledge acquisition, including relationship discovery, metadata inference, summarization, and knowledge graph generation. Partner with engineering and product teams to bring scientific innovations into production at hyperscale.

Required/Minimum Qualifications: Bachelor's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years related experience (e.g., statistics, predictive analytics, research). OR Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 4+ years related experience (e.g., statistics, predictive analytics, research). OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 3+ years related experience (e.g., statistics, predictive analytics, research). OR equivalent experience. Proven track record of translating research into large-scale production systems. Additional or preferred qualifications Other Requirements:  Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include but are not limited to the following specialized security screenings: Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud background check upon hire/transfer and every two years thereafter.

Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years related experience (e.g., statistics, predictive analytics, research) - OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 5+ years related experience (e.g., statistics, predictive analytics, research) - OR equivalent experience. 8+ years of experience across ML with a proven record for applying ML across production systems. Experience with enterprise AI, retrieval systems, agent architectures, or knowledge platforms, evals. Experience building