AI Tester

AI Tester

Posted 1 day ago by 1758010735

Apply
Negotiable
Outside
Hybrid
USA
Apply
Amazon Web Services (AWS) Artificial Intelligence Automation Code Injection Cyber Security DevSecOps Enterprise Security Input/Output Machine Learning Market Trend Microsoft Azure MITRE ATT&CK Framework Open Web Application Security Project (OWASP) Penetration Testing Risk Management Framework Security Strategies Threat Detection

Summary: The AI Tester role at Santander involves conducting adversarial testing on GenAI systems to identify vulnerabilities and enhance security measures. The position requires collaboration with various teams to integrate testing into the security framework and develop tailored testing frameworks. Candidates should have extensive experience in cybersecurity and adversarial testing, with a strong foundation in machine learning principles. The role offers a hybrid working arrangement in Dallas or fully remote options for the right candidate.

Key Responsibilities:

  • Design and execute controlled adversarial attacks on GenAI models.
  • Evaluate models against known and emerging AI-specific attack vectors.
  • Develop reusable test repositories, scripts, and automation.
  • Recommend remediation strategies for discovered vulnerabilities.
  • Continuously monitor the external threat landscape for new attack methods.
  • Correlate findings with internal AI deployments to identify exposure points.
  • Build relationships with threat intelligence providers and regulators.
  • Integrate adversarial testing into the broader enterprise security framework.
  • Collaborate with AI/ML engineering teams to embed adversarial resilience.
  • Provide training and awareness sessions for business units leveraging GenAI.
  • Develop custom adversarial testing frameworks tailored to specific use cases.
  • Evaluate and recommend security tools for AI model monitoring and threat detection.
  • Contribute to enterprise AI security strategy with new practices and technologies.

Key Skills:

  • 5+ years of experience in adversarial testing of GenAI systems.
  • Cybersecurity red-team/penetration testing background.
  • Strong Python/scripting skills for automation and test harnesses.
  • Fundamentals of ML/GenAI and adversarial ML techniques.
  • Familiarity with AI security frameworks (NIST AI RMF, MITRE ATLAS, OWASP Top 10).
  • Experience with AI/MLOps platforms and integration frameworks.

Salary (Rate): undetermined

City: undetermined

Country: USA

Working Arrangements: hybrid

IR35 Status: outside IR35

Seniority Level: undetermined

Industry: IT

Detailed Description From Employer:

Role: AI Tester

Client: Santander

Hybrid in Dallas, TX OR Remote

6+ month contract potential of extension/rolling over to fulltime

Must have LinkedIn. Not created recently.

Subcontracting is not allowed.

Job Description/Key Responsibilities:

  • 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.

Duration:

  • Possibility of FTE conversion

Location:

  • Hybrid position in Dallas OR Fully Remote in the US
  • IF hybrid, workers will be required to report onsite 2 days a week at the Dallas, TX Santander office (this is the HM's preference as most of the team this resource will be joining is already located in Dallas)
  • Open to fully remote candidates as well to find the right fit

Must-Have Requirements:

  • 5+ years of experience
  • Hands-on adversarial testing of GenAI systems (prompt injection/jailbreaks, input output evals, data-exfil testing) with actionable remediation
  • Cybersecurity red-team / penetration testing background and strong Python/scripting for automation and test harnesses
  • ML/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 LLMs
  • Experience with AI/MLOps platforms & integration frameworks (Azure AI or AWS SageMaker; OpenAI API/Hugging Face; LangChain or equivalent) in an enterprise setting

Nice-to-Haves:

  • Exposure to governance/risk for AI (model risk, policy alignment)
  • SIEM/SOAR & threat-intel integration and monitoring
  • Experience with building reusable adversarial test repos, scripts, and automation
Apply
Similar Jobs
Loading data...