Overview
Developing and scaling human-centered model evaluation approaches that combine quantitative and qualitative methods to assess whether AI systems meet user needs in realistic workflows and contexts. Translating user goals, behaviors, and expectations into measurable constructs, eval criteria, rubrics, grading standards, and decision thresholds. Designing and conducting human grading, calibration, and “grade the grader” research to improve the reliability and validity of human and agentic evaluation systems. Partnering with applied scientists and product teams to build representative eval sets, diagnose eval misalignment, and turn research findings into actionable inputs for model and eval development. Establishing a coordinated Office-wide framework for research partnerships with applied science across app-specific and shared teams, including clear engagement models, coverage priorities,
Full job description
Full Job Description
Developing and scaling human-centered model evaluation approaches that combine quantitative and qualitative methods to assess whether AI systems meet user needs in realistic workflows and contexts. Translating user goals, behaviors, and expectations into measurable constructs, eval criteria, rubrics, grading standards, and decision thresholds. Designing and conducting human grading, calibration, and “grade the grader” research to improve the reliability and validity of human and agentic evaluation systems. Partnering with applied scientists and product teams to build representative eval sets, diagnose eval misalignment, and turn research findings into actionable inputs for model and eval development. Establishing a coordinated Office-wide framework for research partnerships with applied science across app-specific and shared teams, including clear engagement models, coverage priorities, reusable methods, and quality standards. Developing reusable tools, processes, templates, guidance, and rhythms that enable researchers to contribute effectively and consistently to model evaluation at scale. Amplifying the role and impact of user research in AI development through compelling storytelling, education, consultation, and visible examples of research influence on model and product quality. Doctorate in Human-Computer Interaction, Human Factors Engineering, Computer Science, Technical Communications, Information Science, Information Architecture, User Experience Design, Behavioral Science, Social Sciences, or related field AND 3+ years User Experience Research experience OR Master's Degree in Human-Computer Interaction, Human Factors Engineering, Computer Science, Technical Communications, Information Science, Information Architecture, User Experience Design, Behavioral Science, Social Sciences, or related field AND 4+ years User Experience Research experience OR Bachelor's Degree in Human-Computer Interaction, Human Factors Engineering, Computer Science, Technical Communications, Information Science, Information Architecture, User Experience Design, Behavioral Science, Social Sciences, or related field AND 6+ years User Experience Research experience OR equivalent experience. Experience applying mixed-methods research approaches, including experimental design, statistical analysis, measurement development, survey or scale design, and synthesis of qualitative and quantitative evidence. Experience translating complex product or user questions into rigorous, valid, and actionable research and evaluation programs. Experience partnering with applied science, data science, engineering, design, or product management teams to influence technical or product decisions. Solid program leadership, project management, organization, and planning skills, with the ability to coordinate work across multiple teams and disciplines across organizational boundaries. Demonstrated ability to apply AI throughout the research workflow and proactively build tools, automations, or reusable solutions that improve research quality, efficiency, and scale. Highly polished written, verbal, and visual communication skills, including the ability to influence senior stakeholders and explain technical or methodological concepts to varied audiences. In-depth experience with AI or machine learning evaluation, including eval-set construction, rubric development, human annotation, grader calibration, error analysis, psychometrics, or LLM-as-a-judge methods. Experience with technical approaches to research and data acquisition, such as scripting, automation, experimentation platforms, telemetry, data pipelines, or visualization. Demonstrated ability to create scalable frameworks, standards, or communities of practice that raise the quality and impact of research across an organization. Experience shaping strategy and driving change in highly ambiguous, cross-organizational environments.
Tips for this job
Practical Job and Scholarship guidance. These tips do not replace official rules or create new eligibility requirements.
- Tailor the CV and application to the responsibilities and required skills stated on the official employer page.
- Use concrete evidence of relevant work, projects and measurable results rather than generic claims.
- Confirm location, work authorization, remote restrictions and sponsorship terms before applying.
- Apply through the original employer or official recruitment destination shown on this page.
Verification notes
Verified from public schema.org JobPosting structured data on the official source page. The complete published description, responsibilities, requirements and benefits were normalized when present; unstated facts were not inferred.
Job and Scholarship is the discovery and verification layer. Confirm eligibility, dates, salary/funding and application instructions on the original source before submitting anything.
Microsoft Opportunities ↗Browse current Job and Scholarship listings from Microsoft Opportunities →
