AI Safety Program Manager

Artificial Intelligence has the potential to change the world around us, but we act ethically along the way. At Microsoft, we are committed to the advancement of AI driven by ethical principles . We are looking for a Program Manager to join us to create a strategy for improving our approach to AI Safety to deliver on that promise. Are you passionate about security and technology in society? This may be a opportunity for you!

Who we are:

We are the Artificial Generative Intelligence Security (AeGIS) team, and we are charged with ensuring justified confidence in the safety of Microsoft's generative AI products. This encompasses providing an infrastructure for AI safety; serving as a coordination point for all things AI incident response; researching the quickly evolving threat landscape; red teaming AI systems for failures; and empowering Microsoft with this knowledge. We partner closely with product engineering teams to mitigate and address the full range of threats that face AI services - from traditional security risks to novel security threats like indirect prompt injection and entirely AI-native threats like the manufacture of NCII or CSAM or the use of AI to run automated scams. We are a mission-driven team intent on delivering trustworthy AI and response processes when it does not live up to those standards.

How we work:

We are always learning. Insatiably curious. We lean into uncertainty, take risks, and learn quickly from our mistakes. We build on each other's ideas, because we are better together. We are motivated every day to empower others to do and achieve more through our technology and innovation. Together we make a difference for all our customers, from end users to Fortune 50 enterprises.

Our team has people from a wide variety of backgrounds, previous work histories, and life experiences, and we are eager to maintain and grow that diversity. Our diversity of backgrounds and experiences enables us to create innovative solutions for our customers. Our culture is collaborative and customer focused.

What we do:

While some aspects of safety can be formalized in software or process, many things require thinking and experience - things like threat modeling, identifying the right places and ways to mitigate risks, and building response strategies. In the world of AI safety, this requires an awareness and understanding of threats far beyond those from traditional security; you don't just need to worry about an access control failure, you need to worry about the user of your system having an abusive partner who's spying on them. The Empowering Microsoft team within AeGIS is charged with continually distilling our understanding of AI safety into training, documentation, and tools that empower the people designing, building, testing, and using systems to do so safely. While the team's top priority is to train Microsoft's own teams, we are looking beyond that to provide these resources to the world at large.

How you can help:

We are searching for an AI Safety Program Manager who can work with a wide range of teams (product, policy, research, incident response, security partner teams, etc.) and stakeholders at all levels, to understand both the broad picture of safety issues and the workflows of teams that need to be aware of them, distill out of this practical lessons and methods to insert safety into every aspect of how teams work, and help package and communicate this distillation effectively. That packaging may take the form of anything from written documents to presentations, to building AI-powered tools that directly assist people.

The candidate will have deep experience one or more of the technical safety disciplines (abuse, cybersecurity, privacy, etc.) with a good understanding the human impact of risks in software systems (e.g. by affecting people's daily lives). They will have an ability to distill a large range of information into core, clear ideas; and have communication skills to effectively convey these ideas in a range of media and fora. Experience with the ways in which real product and engineering teams' function is highly desirable, as solutions that don't fit naturally into real people's workflows aren't useful solutions.

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.

Responsibilities:

• Establish a strategy for improving our approach to AI Safety by working with stakeholders to synthesize issues and identify opportunities to improve our processes, tooling and training through a virtuous feedback loop.
• Designing methodologies for teams to build safely and effectively, with a clear eye towards those being directly useful and applicable by real teams
• Build collaborative relationships with other stakeholder teams working on Responsible AI to scale out AI Safety methodologies
• Other
  • Embody our Culture and Values

Qualifications:

Required Qualifications -

• 5+ years experience in any of the safety disciplines in computer science (abuse, security, privacy, etc.)
• 3+ years experience managing cross-functional and/or cross-team projects.
• Bachelor's Degree AND 6+ years experience in engineering, product/technical program management, data analysis, or product development
  • OR equivalent experience.

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 background and Microsoft Cloud background check upon hire/transfer and every two years thereafter.

Preferred Qualifications -

• Experience in more than one of the safety disciplines in computer science (abuse, security, privacy, etc)
• 1+ year(s) of experience reading and/or writing code (e.g., sample documentation, product demos).
• 8+ years of experience managing cross-functional and/or cross-team projects.
• Bachelor's Degree AND 10+ years experience in engineering, product/technical program management, data analysis, or product development OR equivalent experience.

Technical Program Management IC5 - The typical base pay range for this role across the U.S. is USD $137,600 - $267,000 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 $180,400 - $294,000 per year.

Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here:

https://careers.microsoft.com/us/en/us-corporate-pay

Microsoft will accept applications for the role until August 27, 2024.

Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, color, family or medical care leave, gender identity or expression, genetic information, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran status, race, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable laws, regulations and ordinances. We also consider qualified applicants regardless of criminal histories, consistent with legal requirements. If you need assistance and/or a reasonable accommodation due to a disability during the application or the recruiting process, please send a request via the Accommodation request form .

Benefits/perks listed below may vary depending on the nature of your employment with Microsoft and the country where you work.

#MSECAIR #MSFTSecurity #AI #Safety #Security