Adversarial AI Tester

The Adversarial AI Tester is responsible for evaluating, stress-testing, and validating artificial intelligence and machine learning systems against adversarial threats, misuse, bias, and failure modes. This role plays a critical part in ensuring the robustness, safety, reliability, and ethical performance of AI models across production and pre-production environments.

This position is strictly limited to candidates who currently reside in the United States and are legally authorized to work in the U.S. Applications from individuals residing outside the United States will be rejected.

Key Responsibilities:

Design and execute adversarial testing strategies for AI and machine learning models

Identify vulnerabilities related to model robustness, security, bias, hallucinations, and misuse

Perform red-teaming, prompt injection testing, model evasion testing, and data poisoning simulations

Develop test cases to evaluate AI behavior under malicious, edge-case, or unexpected inputs

Document findings, risks, and mitigation recommendations in clear technical reports

Collaborate with ML engineers, data scientists, and security teams to remediate identified weaknesses

Validate fixes and improvements through regression and re-testing

Support responsible AI, governance, and compliance initiatives

Stay current on emerging adversarial AI techniques, threats, and industry best practices

Required Qualifications:

Bachelors degree in Computer Science, Artificial Intelligence, Cybersecurity, Data Science, or a related field

3–6 years of experience in AI/ML testing, model evaluation, security testing, or red team activities

Strong understanding of machine learning concepts, including supervised and unsupervised models

Experience testing large language models (LLMs), computer vision, or predictive systems

Familiarity with adversarial attack techniques (e.g., prompt injection, model evasion, data poisoning)

Proficiency in Python and common ML frameworks (e.g., PyTorch, TensorFlow, scikit-learn)

Strong analytical, documentation, and communication skills

Ability to work independently in a fully remote environment

Preferred Qualifications:

Masters degree or Ph.D. in AI, Machine Learning, or Cybersecurity

Experience with AI governance, model risk management, or responsible AI frameworks

Familiarity with cloud-based AI platforms (AWS, Azure, GCP)

Knowledge of NIST AI Risk Management Framework or similar standards

Experience with security testing tools, red teaming methodologies, or AI audits

Compensation:

Annual Salary Range: $120,000 – $165,000 USD, based on experience, technical expertise, and geographic location

Benefits:

Comprehensive medical, dental, and vision insurance

401(k) retirement plan with employer matching

Paid time off, paid holidays, and sick leave

Life, short-term, and long-term disability insurance

Flexible remote work schedule

Professional development, research, and certification support

Employee wellness and assistance programs

Work Authorization & Residency Requirement:

Must be legally authorized to work in the United States

Must currently reside within the United States

Applications from candidates outside the U.S. will not be considered