Adversarial AI Defense, Specialist
- Malvern, United States +1
- Mid Level
- Bachelor's degree
- Posted
Skills
Required
- red teaming / adversary emulation / penetration testing
- malware
- reverse engineering
- x86/x64
- .NET
- scripting
- incident response
- forensic reconstruction
- Python
- automation tooling
- LLM/agentic architectures
Preferred
- AI
- threat research / nation-state adversary tracking
- MITRE
- ATT&CK
- ATLAS
- ML
- security analytics
- GREM
About Vanguard
Global Risk and Security (GR&S) at Vanguard enables business strategy, protects client and Vanguard interests (e.g., assets and data), and stewards a strong risk culture.
Our teams leverage enterprise-wide insights, deep expertise, and trusted advice so that across Vanguard leaders and crew drive faster, stronger, risk-informed decisions.
Within GR&S, the Enterprise Security and Fraud (ES&F) sub-division is responsible for the global protection of Vanguard crew, property, data, and client assets.
We are the trusted advisors that protect the pride of Vanguard with state-of-the-art security and fraud capabilities.
We are a world-class destination of highly engaged, passionate, and diverse talent expected to continuously learn and develop in an ever-changing security landscape.
Our crew are our greatest resource – by joining our team you will build collaborative long-term relationships and enjoy a suite of benefits that includes comprehensive health and wellness care, work-life balance, and an investment in your future at its core.
Vanguard At Vanguard, we don't just have a mission—we're on a mission.
To work for the long-term financial wellbeing of our clients.
To learn and develop our skills as individuals and as a team.
From Malvern to Melbourne, our mission drives us forward and inspires us to be our best.
Vanguard has implemented a hybrid working model for the majority of our crew members, designed to capture the benefits of enhanced flexibility while enabling in-person learning, collaboration, and connection.
We believe our mission-driven and highly collaborative culture is a critical enabler to support long-term client outcomes and enrich the employee experience.
Responsibilities
- Build and lead a first-of-its-kind defensive program focused on countering autonomous systems and adversarial AI, including its charter, operating model, and technical roadmap.
- Mentor a team of analysts and engineers across reverse engineering, AI-assisted analysis, building depth in a scarce and fast-moving skill set.
- Identify, test, and validate detective, preventive, and compensating controls built to hold up against AI-driven and autonomous attack techniques, and measure how well they perform under realistic adversary conditions.
- Design and run deception and canary infrastructure.
- Identify, test, and validate deceptive controls, then seed, tune, and maintain canary assets that disrupt, misdirect, and neutralize autonomous adversaries and agentic attack tooling.
- Stand up and maintain a dedicated lab environment to simulate adversarial AI and autonomous attack scenarios and continuously stress-test control effectiveness.
- Recover, triage, and deconstruct malicious binaries, scripts, and payloads through static and dynamic reverse engineering to determine capability, intent, attribution signals, and autonomous behavior patterns.
- AI-assisted pipelines that automate triage and intelligence extraction at volume, and put that intelligence to work across detection engineering, threat hunting, incident response, and threat intelligence functions.
- Turn high-value intelligence into automated detection and response workflows that identify, intercept, and disrupt machine-speed attacks before they reach their objective.
- Map and predict the attack paths autonomous systems and adversarial AI are most likely to take, and use that insight to prioritize where defensive investment goes.
- AI-enabled breach investigations, including forensic reconstruction of events, root cause analysis, and timeline development across complex, fast-moving intrusions.
- Work with red team, cloud security, AI/ML engineering, IAM, and enterprise architecture to build defensive requirements into AI adoption at the design stage rather than retrofitting them later.
- Define KPIs for program maturity, control coverage, and mean time to disrupt, and brief senior leadership and risk committees on the threat landscape and the organization's readiness against it.
- Map program outcomes to NIST AI RMF, MITRE ATT&CK and ATLAS, OWASP LLM Top 10, and evolving AI governance and regulatory requirements.
Requirements
- Minimum of five years related work experience, with three years of experience in red teaming, adversary emulation, or penetration testing.
- Undergraduate degree in a related field or the equivalent combination of training and experience
- Deep malware reverse engineering expertise (x86/x64, .NET, scripting); hands-on incident response and forensic reconstruction; proficiency in Python and automation tooling; working knowledge of LLM/agentic architectures and their attack surfaces; experience building detection or deception capabilities from scratch.
Preferred
- Prior threat research or nation-state adversary tracking experience; familiarity with MITRE ATT&CK and ATLAS; experience applying ML to security analytics; published research or conference presentations; GREM, GCFA, OSCP, or equivalent.
- Special Factors This is a hybrid role, with Tuesday, Wednesday, and Thursday in the office, and Monday and Friday remote.
- Special Factors Sponsorship Vanguard is not offering visa sponsorship for this position.
Benefits
- To lead through product and services that transform our clients' lives.
