The posting
When you join the growing BILH team, you're not just taking a job, you’re making a difference in people’s lives.
A seasoned Red Team professional with experience dealing with AI systems. You will collaborate with AI researchers, product/project managers, and other engineers to proactively test and improve the resilience of our generative AI systems against real-world threats, including prompt injection attacks, data poisoning, and bias exploitation. You will also play a key role in driving red teaming best practices, ethical alignment, and safeguarding the integrity of generative AI models.
Job Description:
Essential Duties & Responsibilities, including but not limited to: 1. Lead and execute red team operations, including targeting AI/ML systems, simulating adversarial attacks such as prompt injections, data poisoning, model inversion, and evasion techniques to identify vulnerabilities in generative AI, computer vision, or natural language processing models.
2. Evaluate AI systems for ethical risks, biases, fairness issues, and harmful content generation, collaborating with trust and safety teams to assess compliance with responsible AI standards and mitigate potential societal impacts.
3. Develop and deploy custom tools, exploits, and automated testing frameworks for AI security assessments, including infrastructure for adversarial input generation and privacy-preserving attacks on federated learning environments.
4. Conduct research on emerging AI threats, publish findings on offensive AI techniques, and integrate AI/ML tools into red team methodologies for enhanced threat simulation and anomaly detection.
5. Mentor junior engineers in AI-specific red teaming practices, lead small teams during engagements, and collaborate with blue teams to validate detections against AI-targeted attacks like jailbreaking large language models.
6. Stay Current: Stay up-to-date on cutting-edge AI security research, adversarial machine learning techniques, and ethical AI frameworks to ensure robust red teaming practices.
7. Collaborate with AI Teams: Work closely with machine learning engineers, data scientists, product managers, and AI researchers to evaluate model performance under adversarial conditions and provide actionable recommendations for strengthening AI defenses.
8. Provide technical support to incident response teams, analyze vulnerabilities during investigations, and assist with corrective measures.
9. Collaborate with blue teams, purple teams, and broader security groups to stress-test systems, validate detection mechanisms, and improve enterprise readiness.
10. Plan, coordinate, and execute full-lifecycle red team operations, including reconnaissance, command and control setup, lateral movement, and adversary emulation to simulate real-world attacks and test organizational defenses.
Minimum Qualifications:
Education: BS Preferred
Licensure, Certification & Registration: Preferred to have certificates: • Certified Ethical Hacker (CEH), OSCP, OSEP, or similar offensive security certifications • AI/ML security certifications
Experience: • 3 – 5 + years of experience in offensive security, penetration testing, or red teaming • 1 - 2+ years of hands-on experience with AI/ML systems and frameworks
Skills, Knowledge & Abilities: • Expertise with red teaming tools (Kali Linux, Metasploit, Wireshark, Burp Suite, etc.) Preferred Qualifications & Skills: • Understanding of machine learning fundamentals and model architectures • Experience with AI model interpretability & automation tools • Traditional penetration testing and red team methodologies
Pay Range:
$125,000.00 USD - $160,000.00 USD
The pay range listed for this position is the annual base salary range the organization reasonably and in good faith expects to pay for this position at this time. Actual compensation is determined based on several factors, that may include seniority, education, training, relevant experience, relevant certifications, geography of work location, job responsibilities, or other applicable factors permissible by law.
