Microsoft Senior AI Security Researcher

New job, posted less than a week ago!

Job Details

Posted date: Dec 03, 2025

There have been 2 jobs posted with the title of Senior AI Security Researcher all time at Microsoft.

Category: Security Research

Location: Multiple Locations, Multiple Locations

Estimated salary: $188,900
Range: $119,800 - $258,000

Employment type: Full-Time

Work location type: 0 days / week in-office – remote

Role: Individual Contributor


Description

Overview

Artificial Intelligence (AI) has the potential to change the world around us. At Microsoft, we are committed to the advancement of AI driven by ethical principles. We are looking for a Senior AI Security Researcher to join a small incubation team to accelerate Microsoft’s capabilities for understanding, detecting, and responding to AI incidents. You will work closely with product engineering teams, the AI security platform team, and centralized function teams to deliver detections and protections against emerging AI threats. This work includes attack discovery, actor tracking, tactics, technique, and procedure identification, and authoring of detections.

This role works broadly across Microsoft on all levels of the AI stack and the teams supporting this important transformation. This is part threat analyst, part investigator, part researcher, and always an advocate for customers and the company. Are you passionate about the safety and security of AI and how that intersects with our lives? This may be a great 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 and security 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 sexual exploitation and abuse material (SEAM) or deep fake production 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.

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 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. Our culture is collaborative and customer focused.

What we do:

The AI Incident Detection & Response team is a small team of subject matter experts that has been brought together to accelerate and support Microsoft’s AI services. Our focus is on the attack frontier understanding the latest threats and actors utilizing AI services. We identify new threats and techniques, help to protect against them, and educate the broader company on the latest threat landscape observations. AI has the potential to transform our daily interaction with technology. Our team keeps the outcome focused on justified confidence in Microsoft’s AI services. We are passionate about ensuring that the transformational opportunities outweigh the possible harms. When harm occurs, we address them in a timely manner. We work to improve and create a more resilient system that enables defenders to protect their AI uses and services. Our team tightly partners throughout Microsoft so that we learn from experience and work to prevent harms before they happen.

How you can help:

We are searching for a seasoned security researcher who is interested in expanding their skills and expertise into the AI realm. The ideal candidate will have demonstrated curiosity in AI, a passion for safety and security, thrive in ambiguity, and delivering results under time constraints. In this global-focused role you are on the attack frontier creating threat intelligence context and insight and ultimately protection against this rapidly evolving world. Help our product engineering teams, defenders, and customers clearly see the threats that matter most and relate that to their service or organization. Listening, understanding, writing, and talking are all part of this role.

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.

This role can sit remote if within 4 hours of posted location

Responsibilities

Independently analyzes business critical security issues (e.g., root cause, motivation, and impact); recommends next steps and escalations to resolve incidents through cross-team collaboration and leveraging your team members. Devises mitigation steps; provides detection and protection signatures to improve defensive posture.

Analyze complex issues using multiple data sources to develop insights that demystify the threat landscape and make it easily discoverable for customers to understand the full operational picture of attacks and the cyber criminals behind them.

Synthesize threat data to generate trends, patterns, and insights that enhance our optics and capability, hunt cyber threats in real-time, and produce intelligence reports and analysis for cyber security stakeholders across Microsoft, our external partners, and our customers.

Collaborate and drive with partners across Microsoft’s security community to innovate new approaches for detecting and tracking threats, adversaries, techniques, tools, and infrastructure in a rapidly evolving threat landscape.

Identify, analyze, and learn across Microsoft’s dataset to develop durable detection solution/strategies across the attack lifecycle or service enhancements to prevent attacks.

Utilize and contribute your research to the large Microsoft threat intelligence community to drive protection and future research advancements based on priority and impact the methods have on customers. Helps others understand triage, analysis, and prioritization of cyber forensics involving AI services.

Develop tools to automate analyses, measure signal-to-noise, and identify variants.

Be part of the diverse Microsoft threat intelligence community by being available to others and drive change through sharing, coaching, and modeling appropriate risk taking and ethical behavior.

Work cross-functionally with engineering, marketing, and business leaders to innovate and deliver security intelligence offerings at a global scale.

Work with product engineering teams to ensure appropriate features to enable defenders investigating and remediating AI-related attacks are available. Advocate for quicker, simpler incident response to match the severity of the threats.

Contribute to the upskilling of partner teams across company to create timely and repeatable response processes.

Advocate for policies and procedures (or changes thereof) that ensure that customers can have justified confidence in Microsoft’s AI services.

Embody our Culture and Values

Qualifications

Required Qualifications:

Doctorate in Statistics, Mathematics, Computer Science, Computer Security, or related field OR Master's Degree in Statistics, Mathematics, Computer Science, Computer Security, or related field AND 3+ years experience in software development lifecycle, large-scale computing, threat analysis or modeling, cybersecurity, vulnerability research, and/or anomaly detection OR Bachelor's Degree in Statistics, Mathematics, Computer Science, Computer Security, or related field AND 4+ years experience in software development lifecycle, large-scale computing, threat analysis or modeling, cybersecurity, vulnerability research, and/or anomaly detection OR equivalent experience. Other Qualifications

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.Preferred Qualifications:

Bachelor's Degree in Statistics, Mathematics, Computer Science or related field AND 5+ years experience in threat analysis or modeling, cybersecurity, vulnerability research, and/or anomaly detection3+ years of experience researching or investigating cyber incidents.Demostrated record of accomplishment of delivering results despite ambiguity, attention to detail, and the ability to collaborate across a large organization, influencing many functions and teams. Demonstrated curiosity to learn about attacker patterns and behaviors Functional understanding of common threat analysis models such as the Diamond Model, Cyber Kill Chain, and MITRE ATT&CK. Demonstrated capability to analyze and coherently present complex threat intelligence information in a meaningful way to drive customer change and prioritize workstreams. Experience working with extremely large data sets, using tools and scripting languages like KQL, Jupyter notebooks, Python, PowerShell, Splunk, SQL, and PowerBI. Platform and web forensic experience including certificate and file hash analysis, Windows system log analysis, tracing and investigating IP addresses and the associated geographies. Knowledge of adversary capabilities, infrastructure, and techniques as well as an understanding of operating system functionality that can be applied to define, develop, and implement the techniques that discover and track the adversaries and threats of today and tomorrow. Interpersonal awareness. Excellent communication skills with an eye for detail and the ability to articulate business needs in cross-group and partner scenarios. A desire to learn, grow, and drive change. Demonstrated knowledge of threat intelligence, incident response methodology, and attacker tradecraft. A solid understanding of Microsoft organizations, technologies and products, especially as they relate to security, will ensure a quick start.

#MSFT Security #MSECAI #AI #RAI #Safety #Security #MSECAIR #AEGIS #AIIR

Security Research IC4 - The typical base pay range for this role across the U.S. is USD $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.

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

This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.

Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.



Email/text job link for Senior AI Security Researcher at Microsoft

Provide your email or phone number to recieve a short message with the job link and details.

Check out other jobs at Microsoft.