Risk Analyst

Payrate: $70.00 - $75.00/hr.

Summary:

We are seeking creative, resilient, and highly motivated AI Red Teamers to join our Red Teaming team. In this role, you will be at the forefront of AI safety, identifying and mitigating risks in our advanced language models. This is intense, high-impact work at the frontier of AI safety — and it offers direct influence on how Company’s AI systems behave in the real world.

Responsibilities:

• Creative Adversarial Testing: Design and execute client, multi-turn adversarial attacks — including emotional manipulation, roleplay, social engineering, and authority exploitation — to bypass model safeguards and surface harmful capabilities.
• Vulnerability Assessment: Evaluate model outputs for actual harm and real-world risk, not just policy violations. Apply Company's user risk taxonomy to prioritize testing across user types, from casual users to agentic systems.
• Agentic and Emerging Threat Testing: Probe for agentic vulnerabilities such as privilege escalation, indirect prompt injection, and scope creep in multi-authority systems — the next frontier of AI risk.
• Data Annotation and Reporting: Generate high-quality human evaluation data by annotating model failures, classifying vulnerabilities, and producing reproducible adversarial test cases that engineering and safety teams can act upon.
• Cross-Functional Collaboration: Partner with AI researchers, engineers, and domain experts to translate findings into actionable improvements. Contribute to refining our red teaming taxonomy, benchmarks, and tooling infrastructure.
• Continuous Learning: Stay current with evolving adversarial techniques, internet subcultures, and AI safety research to continuously sharpen your attack strategies.

Qualifications:

• Creative and Psychological Insight: Background in creative writing, humanities, mental health counseling, psychology, or special education — with a demonstrated ability to construct compelling narratives, exploit linguistic nuance, and identify psychological vulnerabilities.
• Adversarial Mindset: A natural inclination to think like an attacker and push systems to their limits. You should find genuine satisfaction in discovering unexpected failure modes.
• Adaptability: Comfort switching between modalities (text, image, audio, video) and rapidly adjusting to new model behaviors, testing priorities, and task types.
• Communication Skills: Excellent written and verbal communication skills, with the ability to document and explain complex vulnerabilities clearly to both technical and non-technical audiences.
• Resilience and Balance: Capacity to sustain well-being while engaging in psychologically demanding work. This role involves regular exposure to graphic and objectionable content, including violence, exploitation, and self-harm scenarios. Comprehensive wellness support is provided.

Desired Skills:

• Prior experience in professional red teaming, trust & safety, data annotation, or socio-technical risk analysis.
• Familiarity with large language models (LLMs) and generative AI products such as ChatGPT, Claude, or Gemini.
• Basic technical skills in prompt engineering, encoding techniques (e.g., Base64, ROT13), or scripting to complement creative attack vectors.
• Knowledge of AI safety concepts, including RLHF, alignment, and model evaluation frameworks.
• Understanding of internet subcultures and emerging online threats.
• Experience with data annotation pipelines or labeling tools.

Pay Transparency: The typical base pay for this role across the U.S. is: $70.00 - $75.00 /hour. Non-exempt positions are eligible for overtime at a rate of 1.5 times the base hourly rate for all hours worked in excess of 40 in a work week, or as required by state or local law. Final offer amounts, within the base pay set forth above, are determined by factors including your relevant skills, education and experience. Full-time employees are eligible to select from different benefits packages. Packages may include medical, dental, and vision benefits, health savings accounts with qualified medical plan enrollment, 10 paid days off, 3 days paid bereavement leave, 401(k) plan participation with employer match, life and disability insurance, commuter benefits, dependent care flexible spending account, accident insurance, critical illness insurance, hospital indemnity insurance, accommodations and reimbursement for work travel, and discretionary performance or recognition bonus. Sick leave and mobile phone reimbursement provided based on state or local law.

• Consent to Communication and Use of AI Technology: By submitting your application for this position and providing your email address(es) and/or phone number(s), you consent to receive text (SMS), email, and/or voice communication whether automated (including auto telephone dialing systems or automatic text messaging systems), pre-recorded, AI-assisted, or individually initiated from Aditi Consulting, our agents, representatives, or affiliates at the phone number and/or email address you have provided. These communications may include information about potential opportunities and information. Message and data rates may apply. Message frequency may vary.
• You represent and warrant that the email address(es) and/or telephone number(s) you provided to us belong to you and that you are permitted to receive calls, text (SMS) messages, and/or emails at these contacts. You also acknowledge and agree to Aditi Consulting LLC’s use of AI technology during the sourcing process, including calls from an AI Voice Recruiter. AI is used solely to gather data and does not replace human-based decision-making in employment decisions. Calls may be recorded.

• Consent is not a condition of purchasing any property, goods, or services. You may revoke your consent at any time by replying “STOP” to messages or by contacting [email protected].
• For information about our collection, use, and disclosure of applicant's personal information as well as applicants' rights over their personal information, please see our Privacy Policy .

• #AditiConsulting
• # 26 - 03499