Senior Applied Scientist - AI Safety and Security

Microsoft • Redmond, WA

6d

About The Position

Security represents the most critical priorities for our customers in a world awash in digital threats, regulatory scrutiny, and estate complexity. Microsoft Security aspires to make the world a safer place for all. We want to reshape security and empower every user, customer, and developer with a security cloud that protects them with end to end, simplified solutions. The Microsoft Security organization accelerates Microsoft’s mission and bold ambitions to ensure that our company and industry is securing digital technology platforms, devices, and clouds in our customers’ heterogeneous environments, as well as ensuring the security of our own internal estate. Our culture is centered on embracing a growth mindset, a theme of inspiring excellence, and encouraging teams and leaders to bring their best each day. In doing so, we create life-changing innovations that impact billions of lives around the world.
We are seeking a Senior Applied Scientist - AI Safety and Security to join a high impact team sitting at the intersection of cybersecurity and generative AI. As an applied scientist on this team, you will research, conduct experiments, train models, and develop technical innovation for detection of AI abuse as well as mitigations for threats like prompt injection attacks. You will work towards implementing and shipping state-of-the-art techniques for things like metacognition and mechanistic interpretability, partnering closely with our engineering and security research teams to help defend Microsoft’s flagship AI systems and Agentic products.
We are the Artificial Generative Intelligence Security (AeGIS) team, and we are charged with ensuring justified confidence in the safety and security of Microsoft’s generative AI products. This encompasses providing infrastructure for AI safety and security; 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 are a mission-driven team intent on delivering trustworthy AI and response processes when it does not live up to those standards. We are always learning. Insatiably curious. We lean into uncertainty, take risks, and learn quickly from our mistakes. Together we make a difference for all of 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.
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, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 4+ years related experience (e.g., statistics predictive analytics, research) OR Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 3+ years related experience (e.g., statistics, predictive analytics, research) OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 1+ year(s) related experience (e.g., statistics, predictive analytics, research) OR equivalent experience.
• Candidates must be able 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 Cloud background check upon hire/transfer and every two years thereafter.

Nice To Haves

• Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 6+ years related experience (e.g., statistics, predictive analytics, research) OR Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field AND 3+ years related experience (e.g., statistics, predictive analytics, research) OR equivalent experience.
• 3+ years experience creating publications (e.g., patents, libraries, peer-reviewed academic papers).
• Experience presenting at conferences or other events in the outside research/industry community as an invited speaker.
• 3+ years experience conducting research as part of a research program (in academic or industry settings).
• 1+ year(s) experience developing and deploying live production systems, as part of a product team.
• 1+ year(s) experience developing and deploying products or systems at multiple points in the product cycle from ideation to shipping.
• Experience training or fine-tuning models and building ML experimentation systems. Technical experience with ML tools like PyTorch and data toos like Spark.
• Experience with synthetic data generation and data management for evaluation/training
• Experience publishing research papers and/or obtaining patents
• Deep motivation for user-centric AI safety and security, and interest in detections and mitigations
• Experience with large-scale embedding models and transformer architectures.
• Familiarity with advanced concepts in AI safety, such as metacognition and mechanistic interpretability.

Responsibilities

• Advance the science: Design and run experiments, train models, and develop techniques and pipelines in areas like reinforcement learning, fingerprinting, meta-cognition, and mechanistic interpretability — all while upholding best practices in Responsible AI and Privacy-Preserving ML.
• Push state-of-the-art detection and threat hunting capabilities: explore and optimize detection approaches that enable investigators to do sophisticated searches for attack signature similarity and large-scale pattern matching or anomaly detection.
• Drive AI Safety and Security innovation: Partner with Engineering and PM to translate research into product and security platform vision, experimenting with new mitigation approaches like model activation analysis or drift detection.
• Collaborate across Microsoft: Work closely with Microsoft Research, Defender, Azure, AI platform teams, and product groups to bring cutting-edge AI into real-world applications.
• Stay ahead: Keep up with the latest research and foster a thriving applied science culture. Publishing is encouraged, though not required.
• Embody our Culture and Values

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees