Member of Technical Staff – Machine Learning, AI Safety

Overview

As a Member of Technical Staff – Machine Learning, AI Safety, you will develop and implement cutting-edge safety methodologies and mitigations for products that are served to millions of users through Copilot every day. Users turn to Copilot for support in all types of endeavors, making it critical that we ensure our AI systems behave safely and align with organizational values. You may be responsible for developing new methods to evaluate LLMs, experimenting with data collection techniques, implementing safety orchestration methods and mitigations, and training content classifiers to support the Copilot experience. We’re looking for outstanding individuals with experience in machine learning or machine learning infrastructure who are also strong communicators and great teammates. The right candidate takes the initiative and enjoys building world-class, trustworthy AI experiences and products in a fast-paced environment. 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 (U.S.) or 25 miles (non-U.S., country-specific) of that location. This expectation is subject to local law and may vary by jurisdiction.Responsibilities Leverage expertise to uncover potential risks and develop novel mitigation strategies, including data mining, prompt engineering, LLM evaluation, and classifier training. Create and implement comprehensive evaluation frameworks and red-teaming methodologies to assess model safety across diverse scenarios, edge cases, and potential failure modes.
Build automated safety testing systems, generalize safety solutions into repeatable frameworks, and write efficient code for safety model pipelines and intervention systems. Maintain a user-oriented perspective by understanding safety needs from user perspectives, validating safety approaches through user research, and serving as a trusted advisor on AI safety matters
Track advances in AI safety research, identify relevant state-of-the-art techniques, and adapt safety algorithms to drive innovation in production systems serving millions of users.
Embody our culture and values. Qualifications Required Qualifications

Preferred Qualifications