Member of Technical Staff, LLM Evaluation

Overview

As a Member of Technical Staff, LLM Evaluation, you will develop and implement cutting-edge methodologies to help us evaluate how well Copilot performs in real-world usage scenarios. Users turn to Copilot for all types of endeavors, making it critical that we ensure our AI systems effectively help them meet their needs. Our vision for meeting user needs is expansive and includes not only task completion, but also affective aspects of the experience. You will be responsible for developing new methods to evaluate LLMs, train classifiers, experimenting with data collection techniques, and implementing methodologies to provide real-time signals on Copilot performance. We're looking for outstanding individuals with experience in the social sciences, machine learning, and analysis of natural language. The right candidate is a creative problem solver who will work closely with user researchers and product leaders to build automated evaluation frameworks that help us drive improvements in Copilot.

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.

Starting January 26, 2026, MAI employees are expected to work from a designated Microsoft office at least four days a week if they live within 50 miles () or 25 miles (, country-specific) of that location. This expectation is subject to local law and may vary by jurisdiction.

Responsibilities

• Leverage expertise to measure the performance of Copilot, identify failure modes and novel mitigation strategies, including data mining, prompt engineering, LLM as a judge, and classifier training.
• Creative problem solving, navigating complexity with clarity, independently shaping direction and delivering results even when the path isn’t obvious.
• Create and implement comprehensive evaluation frameworks across diverse scenarios, edge cases, and potential failure modes.
• Build automated testing systems, generalize solutions into repeatable frameworks, and write efficient code for model pipelines and intervention systems.
• Maintain a user-oriented perspective by understanding needs from user perspectives, validating approaches through user research, and serving as a trusted advisor on AI matters
• Track advances in research, identify relevant state-of-the-art techniques, and adapt algorithms to drive innovation in production systems serving millions of users.

Qualifications

Required Qualifications

Preferred Qualifications

Data Science IC4 - The typical base pay range for this role across the $119,800 - $234,700 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $158,400 - $258,000 per year.

Data Science IC5 - The typical base pay range for this role across the $139,900 - $274,800 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $188,000 - $304,200 per year. Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here : Microsoft will accept applications and processes offers for these roles on an ongoing basis.Benefits / perks listed below may vary depending on the nature of your employment with Microsoft and the country where you work.Industry leading healthcareEducational resourcesDiscounts on products and servicesSavings and investmentsMaternity and paternity leaveGenerous time awayGiving programsOpportunities to network and connect