Principal Engineer - AI Security (Hybrid)
Pay is based on several factors which vary based on position. These include labor markets and in some instances may include education, work experience and certifications. In addition to your pay, Target cares about and invests in you as a team member, so that you can take care of yourself and your family. Target offers eligible team members and their dependents comprehensive health benefits and programs, which may include medical, vision, dental, life insurance and more, to help you and your family take care of your whole selves. Other benefits for eligible team members include 401(k), employee discount, short term disability, long term disability, paid sick leave, paid national holidays, and paid vacation. Find competitive benefits from financial and education to well-being and beyond at https://corporate.target.com/careers/benefits.
About Us
Working at Target means helping all families discover the joy of everyday life. We bring that vision to life through our values and culture. Learn more about Target here. Target is one of the world’s most recognized brands and one of America’s leading retailers. But behind the brand our guests love, is a culture of continual innovation and right now, we are up to big things! Target’s security team is a place where innovation happens daily. Interested in a culture that combines ongoing learning, engineering excellence, and stellar outcomes? We are too - that’s why we work here. Join our team to improve Target’s security and move the business forward.
As a Principal Engineer - AI Security, you’ll collaborate with technical and leadership teams across Target Tech to assess, validate, and continuously improve the security of AI systems and platforms. You will identify security risks and gaps in existing AI implementations, evaluate the effectiveness of security controls and mitigations, perform architectural and technical reviews, and provide actionable recommendations to strengthen the overall security posture of AI solutions. This role is highly technical, requiring deep expertise in AI security, threat modeling, security controls, testing methodologies, and industry standards. You will serve as a trusted advisor and hands-on expert, helping teams identify emerging risks, validate security assumptions, and drive continuous improvements as AI capabilities are deployed, scaled, and evolved across the enterprise.
Beyond the deep expertise, you have great interpersonal skills: our Principal Engineers are called upon to collaborate across the enterprise and have exceptional communication skills that enable open and cooperative partnerships.
Expect to:
Collaborate with AI platform, product, and engineering teams to evaluate the security posture of AI systems throughout their lifecycle
Assess AI architectures, models, agents, and supporting infrastructure to identify security risks, vulnerabilities, and design weaknesses
Develop and execute security validation strategies for AI systems, including threat modeling, attack simulation, and adversarial testing
Evaluate the effectiveness of existing security controls, guardrails, and mitigations protecting AI applications and platforms
Identify emerging AI-specific threats, attack techniques, and vulnerabilities, and communicate their potential business impact
Recommend risk mitigation strategies and prioritized remediation plans to improve the security and resilience of AI systems
Conduct deep technical reviews of AI products, platforms, and architectures to identify opportunities for security improvement
Partner with engineering teams to validate secure deployment patterns for AI workloads across cloud and hybrid environments
Define security assessment methodologies, testing frameworks, and assurance standards for AI technologies
Provide expert guidance on AI security best practices, including model security, prompt injection defenses, agent security, supply chain security, and data protection
Prioritize high-impact security improvements that measurably reduce risk while enabling innovation and business objectives
Perform hands-on security analysis and testing of complex AI-enabled systems, identifying gaps in architecture, implementation, and operational controls
Collaborate with security, architecture, and engineering teams to continuously improve AI security controls and governance practices
Efficiently assess and communicate security risks to stakeholders, balancing technical realities, business priorities, and organizational objectives
Serve as a trusted advisor on AI security, helping teams make informed decisions as AI capabilities evolve across the enterprise
Core responsibilities of this job are described within this job description. Job duties may change at any time due to business needs.
About You:
4-year degree OR equivalent experience
Polyglot programmer comfortable in many languages across different platforms
10+ years of hands-on experience in technology, with extensive knowledge of cybersecurity domains including Information Protection, Cloud Security (GCP strongly preferred), Networking Security, IAM, Automation, and SIEM
LLM Security expertise (RAG, MCP, Input validation, Sandboxing etc.)
In-depth understanding of OWASP top 10 for Large Language Model Applications
Expertise in AI and ML
Understanding of prompt injection and its various styles (direct, indirect, RAG poisoning, etc) / Familiarity with OWSAP top ten for LLMs
Understanding of MCP auth patterns including dynamic client registration
Knowledge in RAG authorization patterns - "How do you implement RBAC in a RAG?"
Understanding of OAuth roles and flows, and how it pertains to minimizing risky permissions
Experience mitigating the security risks of local coding agents.
Solid understanding of containerization technologies and tools
Seeks out cross-team collaboration opportunities
Demonstrated curiosity and ability to learn
Stays current on relevant technologies with self-directed learning
Excellent written and verbal interpersonal skills with strong presentation abilities
Proven history of effectively utilizing a variety of security tools and technologies across diverse environments. The ideal candidate will not be limited to specific vendors or solutions but will possess the technical depth to comprehend and implement an end-to-end solution that aligns with our reference security architecture's requirements
Good understanding of security management workflows in large enterprise organizations and complex environments
Has a good understanding of the current threat landscape and the challenges that most organizations are facing
In-depth knowledge of security frameworks, standards, and best practices (e.g., NIST, ISO/IEC 27001)
Strong understanding of network security, cryptography, and secure software development
Experience with security technologies, such as firewalls, IDS/IPS, SIEM, and DLP
Excellent analytical, problem-solving, and communication skills
Preferred:
GCP native security product experience LLM Security expertise
Vertex AI experience
AWS or Azure experience
This position will operate as a Hybrid /Flex for Your Day work arrangement based on Target’s needs. A Hybrid /Flex for Your Day work arrangement means the team member’s core role will need to be performed both onsite at the Target HQ MN location the role is assigned to and virtually, depending upon what your role, team and tasks require for that day. Work duties cannot be performed outside of the country of the primary work location, unless otherwise prescribed by Target. Click here if you are curious to learn more about Minnesota.
Benefits Eligibility
Please paste this url into your preferred browser to learn about benefits eligibility for this role: https://tgt.biz/BenefitsForYou_FAmericans with Disabilities Act (ADA)
In compliance with state and federal laws, Target will make reasonable accommodations for applicants with disabilities. If a reasonable accommodation is needed to participate in the job application or interview process, please reach out to candidate.accommodations@HRHelp.Target.com.Non-accommodation-relatedrequests, such as application follow-ups or technical issues, will not be addressed through this channel.