Design and execute adversarial testing strategies for AI and GenAI systems, including jailbreaks, prompt injection, unsafe completions, and ungrounded responses.
Build and maintain automated red-team testing frameworks, evaluation harnesses, and adversarial test suites.
Analyze model and system behavior to identify safety, robustness, and security vulnerabilities.
Document findings and provide clear, actionable remediation guidance to application and platform teams.
Partner with AI/ML engineers to harden applications and workflows based on red-team findings.
Collaborate with QA to integrate adversarial testing into continuous validation and release pipelines.
Coordinate with Security teams on LLM threat modeling, vulnerability escalation, and incident support when safety failures occur.
Contribute to research and prototyping of new adversarial testing techniques and red-team tooling.

Requirements

Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent experience
4–7 years of professional software or AI/ML engineering experience
Hands-on experience building, testing, or evaluating AI/ML or LLM-based systems
Strong proficiency in Python and experience developing automated testing or evaluation frameworks
Experience working with modern cloud platforms such as AWS
Understanding of common GenAI and LLM risk vectors, including prompt injection, jailbreaks, or unsafe outputs
Experience collaborating effectively with engineering, security, and product teams.

Benefits

Medical, dental, vision and life insurance
Retirement savings – 401(k) plan with generous company matching contributions (up to 6%), financial advisory services, potential company discretionary contribution, and a broad investment lineup
Tuition reimbursement up to $5,250/year
Business-casual environment that includes the option to wear jeans
Generous paid time off upon hire – including a paid time off program plus ten paid company holidays and three floating holidays each calendar year
Paid volunteer time — 16 hours per calendar year
Leave of absence programs – including paid parental leave, paid short- and long-term disability, and Family and Medical Leave (FMLA)
Business Resource Groups (BRGs) – BRGs facilitate inclusion and collaboration across our business internally and throughout the communities where we live, work and play.

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard skills

adversarial testingautomated testing frameworksAI/ML engineeringPythonevaluation harnessesred-team testingsafety vulnerabilitiesrobustness analysissecurity vulnerabilitiesGenAI risk vectors

Soft skills

collaborationcommunicationdocumentationactionable guidancepartneringcoordinating

Certifications

Bachelor’s degree in Computer ScienceBachelor’s degree in Engineeringrelated field experience