Risk Analyst III

• AI Red Teaming Specialist III (12-Month W2 Contract)
• Location: Austin, TX (Onsite)
• Duration: 12-Month W2 Contract (Potential for Extension)
• Pay Rate: $40-$52/hour (Depending on Experience)
• About the Opportunity
• Russell Tobin is seeking a creative, resilient, and highly motivated AI Red Teaming Specialist III to support a leading global technology organization working at the forefront of artificial intelligence.This role offers a unique opportunity to help evaluate and improve the safety, reliability, and resilience of advanced AI systems. You will be responsible for identifying vulnerabilities, testing model behaviors, and uncovering potential risks across text, image, audio, and video-based AI technologies.
• The ideal candidate possesses strong critical thinking skills, a creative mindset, and the ability to think like an adversary while maintaining a professional and analytical approach.
• ResponsibilitiesCreative Adversarial Testing
• Design and execute novel multi-turn adversarial scenarios to identify weaknesses in AI systems.
• Develop testing approaches involving roleplay, social engineering, authority manipulation, emotional persuasion, and other creative attack methodologies.
• Explore unconventional prompts and interactions to uncover unexpected system behaviors.
• Vulnerability Assessment
• Analyze AI-generated outputs to identify potential safety, security, and trust-related risks.
• Assess the severity and real-world impact of discovered vulnerabilities.
• Document findings and recommend areas for improvement.
• Emerging Threat Analysis
• Test advanced AI workflows for vulnerabilities such as prompt injection, privilege escalation, instruction conflicts, and scope expansion.
• Evaluate risks associated with increasingly autonomous AI capabilities.
• Annotation & Documentation
• Produce high-quality evaluations, annotations, and reports on model performance.
• Create reproducible test cases that can be leveraged by engineering and research teams.
• Maintain detailed records of findings and testing methodologies.
• Cross-Functional Collaboration
• Partner with researchers, engineers, analysts, and subject matter experts to improve AI safety and system performance.
• Contribute to the development of testing frameworks, benchmarks, and evaluation processes.
• Continuous Learning
• Stay current on emerging AI technologies, adversarial techniques, online communities, and evolving threat landscapes.
• Continuously refine testing strategies and creative attack methodologies.
• Required Qualifications
• 3+ years of relevant professional experience (5+ years preferred).
• Strong creative thinking and narrative construction skills.
• Demonstrated ability to build complex scenarios and identify nuanced vulnerabilities.
• Understanding of human behavior, manipulation tactics, persuasion techniques, or social engineering concepts.
• Adversarial mindset with a passion for identifying weaknesses and failure modes.
• Excellent written and verbal communication skills.
• Strong analytical and problem-solving abilities.
• Ability to work onsite in Austin, TX.
• Comfortable working in a fast-paced environment with evolving priorities.
• Preferred Qualifications
• Prior experience in AI red teaming, trust & safety, security testing, risk analysis, content moderation, or related fields.
• Familiarity with large language models and generative AI platforms.
• Experience with prompt engineering and model evaluation techniques.
• Knowledge of encoding and obfuscation methods such as Base64, ROT13, or similar approaches.
• Basic scripting experience (Python or similar).
• Understanding of AI safety concepts, alignment methodologies, or model evaluation frameworks.
• Experience with data annotation, labeling platforms, or quality review processes.
• Awareness of internet culture, online communities, and emerging digital threats.

Russell Tobin offers eligible employee’s comprehensive healthcare coverage (medical, dental, and vision plans), supplemental coverage (accident insurance, critical illness insurance and hospital indemnity), 401(k)-retirement savings, life & disability insurance, an employee assistance program, legal support, auto, home insurance, pet insurance and employee discounts with preferred vendors.

• Equal Employment Opportunity
• Russell Tobin is an equal opportunity employer. We do not discriminate on the basis of the race, religious creed, color, national origin, ancestry, physical disability, mental disability, reproductive health decision making, medical condition, genetic information, marital status, sex, gender, gender identity, gender expression, age, sexual orientation, veteran or military status, or any other characteristic protected by applicable federal, state, or local law.

• Fair Chance Employment
• Russell Tobin is a Fair Chance employer. We consider all qualified applicants, including those with criminal histories, in a manner consistent with applicable state and local Fair Chance laws and ordinances, including, the California Fair Chance Act and all applicable local Fair Chance ordinances.

• Accommodations
• We are committed to providing reasonable accommodations to applicants and employees with disabilities. If you require a reasonable accommodation to participate in the application or interview process, or to perform the essential functions of this role, please contact us.

Only applicable for San Francisco Candidates: Under the San Francisco Lactation in the Workplace Ordinance, we will provide written notice of lactation accommodation rights, and this notice will automatically be given upon hiring, any inquiry of parental leave or lactation accommodation.