AI Security Engineer

Who You’ll Work With:

GTI, Global Technology Infrastructure, builds and supports AllianceBernstein's global technology infrastructure, which underpins the firm's entire technical operating environment. This includes providing the foundation for IT's robust, innovative solutions that provide critical services to our business partners and that enable the firm to develop and sustain its competitive advantage.

What You’ll Do:

We're looking for an AI Security Engineer to design, implement, manage, and support our infrastructure from emerging threats elevated with the advancement of AI technology. This role sits at the intersection of security engineering and AI - successful candidate will be working closely with AI teams to secure the full lifecycle of our AI products, from data to production.

This is a hands-on technical role: you'll assess AI systems for adversarial vulnerabilities, defend against AI-specific threats like prompt injection and data poisoning, and secure the infrastructure and pipelines that AI models depend on. You'll work closely with AI and engineering teams to build security in from the start, and you'll help the organization keep pace with an area of security that's evolving fast.

This role is a strong fit for someone who has a solid security engineering foundation and wants to specialize in one of the field's fastest-growing and highest-impact areas. You'll bring existing skills in cloud security, Python, and secure infrastructure, and apply them to a new class of risk.

You'll help define what responsible, secure AI development looks like as our organization scales its use of AI - with real ownership over how we identify, prioritize, and close AI-specific security gaps.

This is a uniquely challenging role. AI is moving faster than the security practices meant to protect it, which means this role isn't about maintaining an established playbook - it's about writing one. You'll be tackling problems that barely existed a few years ago: how do you red-team a model instead of a network, how do you catch a prompt injection attack before it reaches production, how do you secure a supply chain that includes model weights instead of just code. It's a rare chance to work at the genuine edge of the security field. And because the discipline is so new, the person in this seat has real room to shape how the organization approaches AI security going forward.

This role supports the security of AI systems that increasingly touch core business operations. The key job responsibilities include, but are not limited to:

• Assess and harden AI systems against adversarial attacks, including evasion, model inversion, and membership inference.

• Identify and mitigate AI-specific risks such as prompt injection, jailbreaking, insecure output handling, and data poisoning.

• Red-team and adversarial test AI models and AI-powered applications before and after deployment.

• Secure the AI supply chain, including model weights, dependencies, and deployment pipelines.

• Apply standard application and cloud security practices (IAM, network segmentation, secrets management) to AI infrastructure.

• Partner with AI and product teams to build security into AI development from the start, not bolted on afterward.

• Support data privacy and governance efforts, including PII handling, data lineage, and alignment with emerging AI risk frameworks.

• Translate technical security findings into clear guidance for both engineering and non-technical stakeholders.

• Be part of our 24x7x365 on call support team for our global internet point-of-presence security infrastructure

• Provide thought leadership in industry and to fellow team members across business and technical project dimensions solving complex business requirements

• Demonstrate forward thinking around where the organization is going and how technology can support these efforts

What We’re Looking For:

• 5-8 years of experience in security engineering, with meaningful exposure to AI systems

• Bachelor's degree in computer science, cybersecurity, or a related field, or equivalent practical experience

• Knowledge of information security principles, theories and concepts, plus advanced knowledge of current systems, networks, or specialized security technologies

• Familiarity with adversarial AI concepts and AI-specific attack vectors

• Hands-on experience red-teaming or adversarial testing an AI-powered product in production

• Strong cross-functional communication skills - able to work fluently with both security and AI teams

• Strong Python skills and familiarity with common AI development frameworks

• Strong analytical skills, demonstrable curiosity in quantitative research and analysis

• Candidate must be a self-starter, a dependable partner, as well as a team player

• Working knowledge of cloud security practices across AWS, GCP, or Azure

• Experience with containerization and CI/CD tooling (Docker, Kubernetes, GitHub Actions, or similar)

• Familiarity with OWASP's Top 10 for LLM Applications or MITRE ATLAS

• Exposure to AI governance frameworks such as the NIST AI Risk Management Framework

• Understanding of TCP/IP

• Hands-on experience in designing, engineering, and implementing secure and resilient infrastructure and defining security strategies, such as: Data Loss Protection, DNS/DHCP, Load Balancing (Local and Global)

About AB

We are a leading global investment management firm offering high-quality research and diversified investment services to institutional clients, retail investors, and private-wealth clients in major markets around the globe. With over 4,000 employees across 57 locations operating in 26 countries and jurisdictions, our ambition is simple: to be the most trusted investment firm in the world. We realize that it's our people who give us a competitive advantage and drive success in the market, and our goal is to create an inclusive culture that rewards hard work.

Our culture of intellectual curiosity and collaboration creates an environment where you can thrive and do your best work. Whether you're producing thought-provoking research, identifying compelling investment opportunities, infusing new technologies into our business or providing thoughtful advice to our clients, we are fully invested in you. If you're ready to challenge your limits and empower your career, join us!

All are encouraged to apply. AB does not discriminate against any employee or applicant for employment on the basis of race, color, religion, creed, ancestry, national origin, sex, age, disability, marital status, citizenship status, sexual orientation, gender identity, military or veteran status or any other basis that is prohibited by applicable law. AB’s policies and practices seek to ensure that employment opportunities are available to all employees and applicants based solely on job-related criteria.