AI Red Team Lead & Expert

Job Description

AI Red Team Lead & Expert

We are seeking a highly skilled and mission-driven AI Red Team Lead & Expert to join our AI Risk & Red Teaming practice. In this role, you will work on adversarial testing efforts across a range of AI-enabled systems, including LLMs, chatbots, agents, and multimodal models. You will play a critical role in testing AI systems to identify safety vulnerabilities, high-risk harms, behaviors, and security exposures, contributing directly to the development of responsible and resilient AI technologies.

Key Responsibilities: 

• Lead AI Red Team Engagements:
   Plan, scope, and execute red teaming operations against AI/ML systems including LLMs, generative models, and AI-integrated applications.
• Adversarial Prompt Engineering:
   Design and deploy advanced adversarial inputs to uncover harmful, biased, deceptive, or unsafe outputs from AI models.
• Threat & Risk Assessment:
   Identify and assess high-impact risk scenarios including jailbreaks, misuse vectors, data leakage, prompt injection, and model hallucinations.
• AI Architecture & Model Understanding:
   Collaborate with engineering and research teams to understand system internals and tailor red team strategies accordingly.
• Safety and Security Testing:
   Develop and execute test plans that simulate realistic threats to model alignment, user privacy, system integrity, and public safety.
• Tooling & Automation:
   Build or leverage internal/external tools to scale adversarial testing and track vulnerabilities over time.
• Collaboration & Reporting:
   Partner with cross-functional stakeholders in AI/ML engineering, product, compliance, and legal to communicate red team findings and recommend mitigations.
• Policy & Framework Development:
   Contribute to the creation and refinement of red teaming frameworks, evaluation rubrics, and responsible AI policies.
• Mentorship & Thought Leadership:
   Provide guidance to junior red teamers and represent the team at industry forums, conferences, or standards-setting organizations.

Qualifications:

Required:

• 3+ years of experience in AI/ML, security testing, or applied research, with a focus on adversarial testing or red teaming
• Strong background in AI architecture, including familiarity with LLMs (e.g., GPT, Claude, LLaMA), embeddings, and transformer-based models
• Hands-on experience in adversarial prompt engineering and exploiting model vulnerabilities
• Experience testing or evaluating chatbots, agentic systems, or other AI-enabled applications in real-world scenarios
• Deep understanding of AI safety, alignment, fairness, and ethical risk vectors
  
• Excellent written and verbal communication skills with the ability to produce structured reports for both technical and non-technical audiences

Preferred:

• Prior experience in a dedicated AI Red Team, security research, or offensive security capacity
• Familiarity with prompt injection, jailbreaks, covert instruction attacks, and prompt leakage
• Experience with automated evaluation frameworks, synthetic dataset generation, or multi-modal adversarial testing
• Familiarity with AI regulations and safety standards (e.g., NIST AI RMF, ISO 42001, EU AI Act)
• Experience working with distributed systems, data privacy mechanisms, or reinforcement learning from human feedback (RLHF)

Salary range for this position is included in accordance with current state/local pay transparency legislation. Please note that salaries may vary for different individuals in the same role based on several factors, including but not limited to location of the role, individual competencies, education/professional certifications, experience, and performance in the role.

Base Salary Range: $140,000 – $200,000 

What Makes Applause a Great Place to Work:

Applause is a world leader in digital quality testing. Since 2007, Applause has been the driving force in testing and digital quality innovation. Our expertise continues to help leading brands deliver quality digital products to their customers. Utilizing the skills of 1.5+ million testers in more than 200 countries and territories, Applause helps the world’s leading brands to deliver quality digital products and experiences to their customers on a global scale. With insightful, actionable testing results that can directly inform go/no go release decisions, we enable our customers to release digital products and experiences better, faster and with confidence.

At Applause, living our core values – In it Together, Be Accountable, Create Value for Our Customers, Celebrate Authenticity, and Crush Your Goals – informs our choices as individuals, as teammates and in our everyday interactions with customers. Our values help to keep us on track to deliver the best outcomes, and to be the very best team we can. Embracing a culture of respect, authenticity and inclusion, we value and celebrate diversity.  Together as one Applause Nation, we strive to enable professional opportunities for all employees.

Please visit https://www.applause.com/life-at-applause to learn more about the employee experience at Applause Nation!

Applause is a place where everyone belongs and where we believe everyone deserves the exceptional. Since our founding, we have continued to celebrate diversity and are committed to creating an inclusive environment.  If you believe you require a reasonable accommodation under any of the legally protected characteristics, please click hereto complete an accommodation request. Please note Applause will only review requests for applications that have been submitted. We will review your qualifications and follow up with you regarding your request if your qualifications meet our current needs.

#LI-OB1