Microsofts 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.
In alignment with our Microsoft values, we are committed to cultivating an inclusive work environment for all employees to positively impact our culture every day.
Responsibilities
Become a founding member of the AIAL group as part of Microsoft Red Team:
You will help shape the teams culture and practices.
You will research and discover zero-day vulnerabilities in AI applications, models, and AI service ecosystems.
You will work closely with Red Team operators and engineering teams to address findings and strengthen the resilience of AI-driven systems.
You will analyze a wide array of data sources to identify potential security weaknesses and breach points within Microsofts AI infrastructure.
You will develop tools and techniques to scale and accelerate adversary emulation and vulnerability discovery.
You will advocate for security change across the company by building partnerships and clearly communicating the impact of risks.
Requirements: Our team focuses on the diversity of all types of candidates, and we strive to hire people with different experiences and perspectives into our teams. To that end, we know that no candidate has every desired skill and experience, but together we make a strong, effective teams.
You have a B.Sc. or M.Sc. in Statistics, Mathematics, Computer Science or related field **OR** relevant practical experience (e.g. hands-on work in industry or service in a technology unit in the military).
You have 6+ years of hands-on experience in security research, including 3+ years in vulnerability security research.
A drive to tackle hard problems with a high level of ambiguity.
Knowledge of the security threat landscape, with experience in the modern attacker kill chain and MITRE ATT&CK - especially in AI-related threat scenarios.
Preferred Qualifications
Proficiency in multiple programming and scripting languages.
Proven track record of discovering and responsibly disclosing security vulnerabilities.
Experience in Red Teaming or offensive cyber operations.
You have 6+ years of hands-on experience in vulnerability security research.
Hands-on experience with AI/ML systems, including understanding of model architectures,
adversarial ML, data poisoning, prompt injection, or security of LLM-based applications.
Familiarity with emerging AI security risks, evaluation frameworks, or red teaming AI applications.
.המשרה מיועדת לנשים ולגברים כאחד