About the job
The Copilot Security Engineering team is at the core of Microsoft’s mission to deliver secured , trusted, human-centered AI experiences across the company’s Copilot offerings. We design, build, and operate systems that help identify, evaluate, and mitigate emerging AI security threats, covering adversarial testing frameworks, telemetry pipelines, evaluation systems, and production security defenses. Our goal is to be the industry leader in delivering best-in-class AI security protections for our enterprise customers. We are looking for a Senior Research Engineer (Machine Learning Engineer) who is passionate about translating research ideas into scalable, reliable ML systems. This role is ideal for candidates with strong engineering fundamentals and experience in the security domain and working with machine learning systems, along with an interest in prototyping, experimentation, and system-building. You will partner closely with Applied Scientists, Software Engineers, Product Managers, and Data Scientists to bring AI innovations into production reality and deliver reliable, high-performing security solutions for Copilot.
Responsibilities
Design, deploy, and operate production-scale ML systems that protect Copilot experiences, ensuring high reliability, performance, and security at global scale, targeting threats such as prompt injections, adversarial inputs, and agentic workflow abuse.
Develop adaptive detection and policy models that are capable of learning from evolving attacker behavior to offer durable protection against emerging AI security threats.
Build and own evaluation frameworks for AI security, including adversarial testing, red‑teaming support, and continuous robustness measurement across real Copilot scenarios.
Define success metrics and conduct rigorous experimentation to quantify security effectiveness, adversarial robustness, precision/recall tradeoffs, and user experience impact.
Partner with security and engineering teams to integrate ML defenses into secure orchestration frameworks that govern agent delegation, tool calling, and action execution.
Monitor and analyze telemetry to improve model performance, reduce false positives/negatives, and guide iterative defense improvements.
Collaborate cross‑functionally with product, privacy, and AI platform teams to land agentic security patterns across Microsoft Copilot ecosystem.
Document and share applied ML security techniques, helping establish best practices for secure agentic AI across Microsoft.
On-call Engineering Duties
Qualifications
Minimum
Bachelor's Degree in Computer Science or related technical field AND 4+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or PythonOR equivalent experience.
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.
Preferred
Master's Degree in Computer Science or related technical field AND 6+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or PythonOR equivalent experience.
Bachelor's Degree in Computer Science or related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or PythonOR equivalent experience.
4+ years of hands-on experience building and shipping machine learning, detection, ranking, classification, or data-driven decision systems in production.
Experience building systems related to adversarial testing, evaluation frameworks, telemetry/observability pipelines, or risk‑measurement infrastructure.
Solid foundation in ML fundamentals, including classification, anomaly detection, representation learning, and model evaluation.
Experience designing end to end ML pipelines: data collection, training, evaluation, deployment, and monitoring.
Understanding of agentic AI risks (e.g., jailbreaks, prompt injection, toolchain misuse) and threat‑driven engineering.
Experience working on AI safety, trust, or security adjacent ML problems, including prompt injection, abuse detection, or adversarial ML.
Familiarity with distributed systems, cloud-based services, secure system design patterns, or security-sensitive production environments.
Ability to clearly communicate complex ML and security concepts to engineering and non ML stakeholders.