8 hours ago
Base Salary
$120k - $261k/yr
Responsibilities
- Design, deploy, and operate production-scale ML systems that protect Copilot from prompt injections, adversarial inputs, and agentic workflow abuse.
- Develop adaptive detection and policy models that respond to evolving attacker behavior.
- Build AI security evaluation frameworks, adversarial testing capabilities, red-team support, and continuous robustness measurement.
- Define security effectiveness metrics and run experiments covering adversarial robustness, precision/recall, and user experience impact.
- Integrate ML defenses into secure orchestration frameworks governing agent delegation, tool calling, and action execution.
- Monitor telemetry to improve model performance and reduce false positives and false negatives.
- Partner with product, privacy, security, engineering, and AI platform teams to deploy secure agentic AI patterns across Copilot.
- Document applied ML security techniques and establish reusable security best practices.
- Perform on-call engineering duties.
Requirements
- Bachelor’s degree in Computer Science or a related technical field and 4+ years of technical engineering experience with coding in C, C++, C#, Java, JavaScript, or Python, or equivalent experience.
- Ability to pass Microsoft, customer, and/or government security screening requirements, including the Microsoft Cloud Background Check.
- Preferred: Master’s degree and 6+ years of technical engineering experience, or bachelor’s degree and 8+ years of experience, or equivalent experience.
- Experience designing, building, and operating security-critical production software systems with responsibility for correctness, availability, performance, and maintainability.
- Experience with threat modeling, vulnerability remediation, security defenses, distributed systems, identity, authorization, telemetry, and failure isolation.
- Experience with vulnerability research, red teaming, adversarial testing, incident response, post-incident analysis, and durable security improvements.
- Experience creating platform-level security solutions, risk-management frameworks, security metrics, dashboards, or evaluation pipelines.
- Experience serving as a technical lead or architectural reviewer, mentoring engineers, and communicating security tradeoffs to technical and executive stakeholders.
- Experience securing AI-driven, agentic, tool-invoking, prompt-based, or generative AI systems.
- Ability to operate effectively in ambiguous and rapidly evolving security environments.
Benefits
- The position includes on-call engineering duties.
- Microsoft Cloud Background Check is required upon hire or transfer and every two years thereafter.
- The position is open for a minimum of five days, with applications accepted on an ongoing basis until filled.
- Certain roles may be eligible for benefits and other compensation.
Tech Stack
Categories
About Microsoft
Microsoft develops operating systems, productivity software, cloud services, developer tools, and consumer devices for individuals, enterprises, and governments. Its main products include Windows, Microsoft 365, Azure, Visual Studio/GitHub, Xbox, and LinkedIn; revenue comes from software subscriptions and licenses, cloud consumption, hardware sales, and advertising. Founded in 1975 and headquartered in Redmond, Washington, Microsoft is a public company traded on Nasdaq.