Senior Researcher, Security & AI

About the Role

Microsoft Research India (MSR India) is seeking a Senior Researcher focused on Security & AI. This role involves advancing research at the intersection of security and artificial intelligence, both in securing AI systems and using AI to enhance security. The position offers opportunities to contribute to long-term research problems and translate advances into systems deployed at Microsoft scale, collaborating with researchers and engineers globally.

Key Responsibilities

• Lead research at the intersection of security and AI, covering securing AI systems and applying AI to security problems.
• Develop techniques to protect sensitive data in AI systems and pipelines (training, post-training, reinforcement learning, inference, agentic workflows).
• Investigate the security of AI agents and autonomous systems, addressing attacks from tool use, code execution, memory, external data, multi-agent interaction, and long-running behavior, and developing defenses.
• Explore AI applications in security, including vulnerability and attack path discovery, understanding security environments, attack/behavior detection, and defense development.
• Investigate new attacks enabled or amplified by AI advances and develop robust defenses.
• Design threat models, benchmarks, evaluations, and experimental methodologies for AI security problems.
• Form hypotheses, build prototypes, design experiments, and evaluate new security mechanisms in realistic environments.
• Pursue long-term research and identify opportunities to translate ideas into practical security mechanisms.
• Publish at top-tier venues (security, systems, cryptography, machine learning), release research artifacts, and shape the research agenda in security and AI.
• Collaborate with research and product teams to translate research into stronger security for real-world Microsoft systems.
• Mentor interns and entry-level researchers, and contribute to MSR India's academic and research engagement.

Requirements & Tech Stack

• Passion for advancing the state of the art in security, privacy, cryptography, systems, and AI.
• Strong research track record, demonstrated through publications at top venues (e.g., IEEE S&P, USENIX Security, ACM CCS, NDSS) or leading security, systems, cryptography, or machine learning venues.
• Excitement for tackling emerging security problems created by AI and agentic systems.
• Combination of scientific rigor, strong systems thinking, and ability to turn research ideas into working prototypes.
• Ability to thrive in a highly collaborative, interdisciplinary research environment.
• Aptitude for taking end-to-end ownership of open-ended research problems.

Qualifications

• PhD in Computer Science, Computer Engineering, Mathematics, or a related technical field, or equivalent experience.
• 1+ years of software engineering or research experience.
• Strong background in one or more areas of computer security, privacy, cryptography, computer systems, or machine learning.
• Demonstrated ability to conduct independent research and communicate results through publications, prototypes, open-source artifacts, or other impactful outcomes.
• Ability to identify and formulate important research problems, develop novel technical approaches, and evaluate them rigorously.
• Ability to work effectively across disciplinary boundaries and collaborate with diverse research and engineering teams.

Preferred Qualifications

• Research experience in AI security, security of LLMs, or security of agentic systems.
• Experience with security and privacy techniques for AI training, post-training, inference, or data pipelines.
• Experience in areas such as systems security, applied cryptography, privacy-enhancing technologies, confidential computing, access control, or secure machine learning.
• Experience studying adversarial behavior, software vulnerabilities, attack surfaces, or security of large-scale systems.
• Experience applying LLMs or other AI techniques to security problems (e.g., vulnerability discovery, security analysis, attack detection, defense generation).
• Experience building and evaluating large-scale security or AI systems.
• Experience designing threat models, security benchmarks, adversarial evaluations, or red-team methodologies for emerging systems.
• Experience working across the research-to-production boundary and translating research ideas into real-world systems.