Senior Applied Scientist

Microsoft•Redmond, WA

16h

About The Position

The Copilot Offline Evaluation Platform (COEP) team provides the evaluation data, environments, and capabilities that Microsoft Copilot product teams use to make faster, more confident release decisions. We are seeking a Senior Applied Scientist to improve how well offline evaluations represent and predict real customer experiences. You will develop scientific methods for extracting representative query and intent patterns from Copilot traffic, generating high-quality synthetic evaluation data, measuring and improving query-set and tenant representativeness, reproducing customer dissatisfaction scenarios as compliant evalsets, and increasing alignment between offline evaluation results and online shadow experiments. You will partner closely with engineering, product, and research teams to turn these methods into scalable capabilities used across Copilot, including evaluation of long-running agents and generative AI systems. Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

Requirements

Bachelor's Degree in Statistics, Computer Science, Electrical or Computer Engineering, or related field AND 4+ years related experience (e.g., generative AI, agentic evaluation, LLM, research)
Master's Degree in Statistics, Computer Science, Electrical or Computer Engineering, or related field AND 3+ years related experience (e.g., generative AI, agentic evaluation, LLM, research)
Doctorate in Statistics, Computer Science, Electrical or Computer Engineering, or related field AND 1+ year(s) related experience (e.g., generative AI, agentic evaluation, LLM, research)
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.

Nice To Haves

Master's Degree in Statistics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years related experience (e.g., generative AI, agentic evaluation, LLM, research)
Doctorate in Statistics, Computer Science, Electrical or Computer Engineering, or related field AND 3+ years related experience(e.g., generative AI, agentic evaluation, LLM, research)
equivalent experience.
Experience building, deploying, and operating production machine learning systems at scale.
Experience with deep learning, generative AI, large language models, natural language processing, recommender systems, computer vision, or another area relevant to the hiring team.
Experience with responsible AI, model safety, privacy, fairness, robustness, and evaluation.
Strong written and verbal communication skills, including communicating technical results to diverse stakeholders.
Evidence of technical leadership through mentoring, cross-team collaboration, patents, or publications.
Experience in Privacy-Preserving ML, Synthetic Data Generation, and LLM/Agentic Evaluation would be valuable.

Responsibilities

Frame complex product and customer problems as applied science opportunities with clear success metrics.
Design, build, and evaluate machine learning and AI models, algorithms, and experimentation frameworks.
Develop robust data, training, evaluation, and inference pipelines suitable for production use.
Conduct rigorous offline and online experiments; analyze results and communicate actionable recommendations.
Partner with software engineers and product managers to integrate scientific solutions into products and services.
Improve model quality, reliability, efficiency, safety, and responsible AI practices throughout the lifecycle.
Provide technical leadership through design reviews, mentoring, and raising the scientific bar for the team.
Stay current with relevant research and identify opportunities to apply new methods to customer needs.