Operations Specialist III (6197)

itD is seeking an AI Red Teaming Specialist (Operations Specialist III) to help identify, evaluate, and mitigate risks in advanced AI systems. This role plays a critical part in ensuring the safety, reliability, and responsible deployment of generative AI technologies by uncovering vulnerabilities that require human creativity, psychological insight, and adversarial thinking. The ideal candidate will bring strong expertise in narrative construction, social engineering concepts, and adversarial testing, along with a proven ability to identify complex failure modes and translate findings into actionable improvements.

• →Design and execute creative, multi-turn adversarial attacks using techniques such as roleplay, emotional manipulation, social engineering, and authority exploitation to identify AI model weaknesses.
• →Evaluate AI-generated outputs for real-world harm, risk severity, and safety concerns using established risk assessment frameworks.
• →Investigate emerging AI threats, including prompt injection, privilege escalation, scope creep, and agentic system vulnerabilities.
• →Annotate model failures, classify vulnerabilities, and develop reproducible adversarial test cases for engineering and safety teams.
• →Collaborate closely with AI researchers, engineers, and cross-functional stakeholders to improve model safety and performance.
• →Contribute to the development and refinement of red teaming methodologies, testing benchmarks, taxonomies, and tooling infrastructure.
• →Perform testing across multiple modalities, including text, image, audio, and video-based AI systems.
• →Research evolving adversarial techniques, internet subcultures, and AI safety trends to continuously improve testing effectiveness.

• →Attend regular internal practice community meetings.
• →Collaborate with your itD practice team on industry thought leadership.
• →Complete client case studies and learning material (blogs, media material).
• →Build out material to contribute to the Digital Transformation practice.
• →Attend internal itD networking events (in person and virtual).
• →Work with leadership on career fast-track opportunities.

• 3+ years of relevant professional experience (5+ years preferred for senior-level candidates).
• Demonstrated experience in creative writing, narrative development, humanities, psychology, counseling, special education, or related disciplines requiring advanced communication and behavioral analysis skills.
• Strong ability to construct complex, multi-turn scenarios that leverage linguistic nuance and social engineering techniques.
• Deep understanding of psychological manipulation tactics, human behavior, and vulnerability identification.
• Proven adversarial mindset with the ability to systematically identify, test, and exploit failure modes in AI systems or similar environments.
• Excellent written and verbal communication skills with the ability to clearly document findings for technical and non-technical audiences.
• Ability to work professionally with exposure to graphic, sensitive, and objectionable content.
• Strong critical thinking, analytical reasoning, and problem-solving skills.

• Professional experience in AI red teaming, cybersecurity red teaming, trust and safety, content moderation, or socio-technical risk analysis.
• Familiarity with large language models (LLMs) and generative AI platforms such as ChatGPT, Claude, Gemini, or similar technologies.
• Experience with prompt engineering, jailbreak methodologies, and adversarial testing techniques.
• Knowledge of encoding and obfuscation techniques such as Base64, ROT13, Unicode manipulation, or related methods.
• Basic scripting experience using Python or similar programming languages.
• Understanding of AI safety concepts including RLHF, alignment, model evaluation frameworks, and responsible AI practices.
• Experience working with data annotation, labeling workflows, or evaluation pipelines.
• Knowledge of internet culture, online communities, and emerging digital threats.

Bachelor’s degree in Psychology, Communications, English, Humanities, Behavioral Sciences, Computer Science, Cybersecurity, or a related field, or equivalent professional experience.