Position : AI Security Tester (Application Security)
Client : Large banking organization
Duration : 6+ Months; Strong potential to extend up to 18 months and / or full time conversion
Location : Hybrid 2-3 days in Boston or Dallas office.
Overview :
Adversarial Testing :
- Design and execute controlled adversarial attacks (prompt injection, input / output evaluation, data exfiltration, misinformation generation)
- Evaluate GenAI models against known and emerging AI-specific attack vectors.
- Develop reusable test repositories, scripts, and automation to continuously challenge models.
- Partner with developers to recommend remediation strategies for discovered vulnerabilities.
Threat Monitoring & Intelligence :
Continuously monitor the external threat landscape for new GenAI-related attack methods (e.g., malicious prompt engineering, fine-tuned model abuse).Correlate findings with internal AI deployments to identify potential exposure points.Complete assessment of existing technical controls and identify enhancements.Build relationships with threat intelligence providers, industry groups, and government regulators to stay ahead of adversarial AI trends.Cross-Functional Collaboration :
Partner with Cybersecurity, SOC, and DevSecOps teams to integrate adversarial testing into the broader enterprise security framework.Collaborate with AI / ML engineering teams to embed adversarial resilience into the development lifecycle ("shift-left" AI security).Provide training and awareness sessions for business units leveraging GenAI.Continuous Improvement & Innovation :
Develop custom adversarial testing frameworks tailored to the organization's specific use cases.Evaluate and recommend security tools and platforms for AI model monitoring, testing, and threat detection.Contribute to enterprise AI security strategy by bringing forward new practices, frameworks, and technologies.Must-Have Requirements :
5+ years of experienceHands-on adversarial testing of GenAI systems (prompt injection / jailbreaks, input-output evals, data-exfil testing) with actionable remediationCybersecurity red-team / penetration testing background and strong Python / scripting for automation and test harnessesML / GenAI fundamentals (LLMs, embeddings, diffusion models) and adversarial ML techniques (model extraction, poisoning, prompt injection).Familiarity with AI security frameworks : NIST AI RMF or MITRE ATLAS or OWASP Top 10 for LLMsExperience with AI / MLOps platforms & integration frameworks (Azure AI or AWS SageMaker; OpenAI API / Hugging Face; LangChain or equivalent) in an enterprise settingNice-to-Haves :
Exposure to governance / risk for AI (model risk, policy alignment)SIEM / SOAR & threat-intel integration and monitoringExperience with building reusable adversarial test repos, scripts, and automationRequired Skills : Must-Haves (Concepts & Tools) :
Strong hands on experience with application security testing, pen testing and threat modelingAI experience : should have hands-on adversarial testing of GenAI systems (more functional, prompt injection / jailbreaks, input-output evals, data exfil testing) with actionable remediationstrong Python / scripting for automation and test harnessesFamiliarity with AI security frameworks : NIST AI RMF or MITRE ATLAS or OWASP Top 10 for LLMsExperience with AI / MLOps platforms & integration frameworks (Azure AI or AWS SageMaker; OpenAI API / Hugging Face; LangChain or equivalent) in an enterprise settingBasic Qualification :
Additional Skills :
Background Check : Yes
Drug Screen : Yes
Notes :
Selling points for candidate :
Project Verification Info : The information provided below is for Apex Systems AV use only and is not to be distributed publicly, or to any third party. Any distribution of the below information will result in corrective action from Apex Systems Vendor Management. MSA : Blanket Approval Received Client Letter : Will Not Provide
Exclusive to Apex : No
Face to face interview required : No
Candidate must be local : No
Candidate must be authorized to work without sponsorship : : No
Interview times set : Yes
Type of project : Master Job Title :
Branch Code :