QualificationsAzurePenetration testingPyTorchNumPyDeep learning
The Microsoft AI Red Team supports this mission by elevating awareness of AI security threats and proactively assessing productionized machine learning systems. We empower our customers (including Microsoft) to protect, detect, respond to, and remediate threats against their ML systems wherever they are deployed. This is a greenfield opportunity to shape the burgeoning field of AI Security, as well as to build security solutions for AI systems.
Our team conducts security engagements with ML-based products and services across Microsoft and our partners. We perform scoped research to enable engagements and contribute to internal tooling to scale assessment work. We also engage with the community to increase awareness about AI Security.
Now let’s talk about you. We are looking for a security researcher who is interested in the security of ML systems. This is a very “hands-on” role, with an expectation of practical prototyping more than academic elegance or polish. You will work with other internal red teams, MSR Researchers, and platform engineers to help shape the security of AI systems for Microsoft and our customers.
Responsibilities
Conduct red team assessments against systems that include ML models at Microsoft. This includes writing detailed reports of operational activities, findings and AI Security recommendations.
Contribute to internal automation tooling to probe the integrity and confidentiality of AI systems that operate over a variety of data types, including tabular data, images, audio, video and text.
Conduct scoped research to enable ongoing or upcoming operations. This may include adapting published algorithms for practical settings to evade, infer, invert, poison or to demonstrate harm or abuse using ML models.
Keep up with advancements in adversarial machine learning research and collaborate with the product team to evaluate potential new attacks.
Qualifications
Required Qualifications:
5+ years of industry experience
5+ years of experience in training and deploying ML models
5+ years of experience with Python
4+ years of experience with scikit-learn
2+ years of pytorch, tensorflow and/or other deep learning framework
1+ years professional experience, coursework or demonstratable self-study with adversarial ML: generating adversarial examples, model inversion, membership inference, poisoning, etc.
Preferred Qualifications:
Experience in penetration testing or red teaming
A passion for security and machine learning
Experience deploying productionized machine learning systems
4+ years of experience with numpy
2+ years of experience using GitHub, Azure DevOps or similar
1+ years of experience building cloud services using Microsoft Azure, AWS, or GCP
Strong problem solving and debugging skills
Growth mindset: excited to learn and to help others learn
Creative, out-of-the-box problem solver
Hands-on and crafty, enjoy building things to solve unbounded problems
Excellent written and verbal communication skills, with the ability to simplify and explain complex concepts
Ability to work independently to actively identify and drive solutions for evolving business problems
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 Cloud background check upon hire/transfer and every two years thereafter.
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.
#AzureSecOpen