AI Security Engineer (m/w/d)

Company Overview:
At Machine Learning Reply, we provide cutting-edge consulting services at the intersection of cybersecurity and AI. Our team of experts helps businesses protect their AI-driven systems, data pipelines, and cloud infrastructures from evolving security threats. We are passionate about making AI safer, more ethical, and more resilient for companies across industries. As we continue to expand, we’re looking for a skilled AI Security Engineer to join our consulting team and deliver cybersecurity solutions to our clients.

About the Role

We are searching for an AI Security Engineer (Consultant) to join our consulting team, responsible for identifying and mitigating security vulnerabilities specific to AI models and data. This role requires proficiency in strong cybersecurity practices, Cloud Computing and/or AI Frameworks to address the unique security challenges AI presents. You will collaborate with clients to implement secure AI and Data architectures, assess risk factors, and provide guidance on best practices for ethical and secure AI deployment. Ideal candidates may come from either an cybersecurity and/or AI background but should have a strong interest in bridging both fields within a consulting setting.

Responsibilities:

• Conduct in-depth AI model security assessments, focusing on risks such as model poisoning, prompt injection, and unauthorized access, with an emphasis on protecting data integrity and access control.
• Implement responsible AI frameworks by conducting fairness audits, bias analysis, and explainable AI reviews to align with ethical guidelines.
• Design automated threat detection systems using AI-driven tools to deliver continuous insights and strengthen security models.
• Safeguard intellectual property and AI-generated outputs through secure access layers, content verification methods, and watermarking.
• Perform code security scans and optimize workflows with advanced AI security tools, ensuring compliance with security standards.
• Interface with clients to understand security needs, delivering concise, actionable security recommendations and consulting on AI security frameworks.

• Education: Bachelor’s or Master’s degree in Computer Science, Cybersecurity, AI, Data, or a related field.
• Technical Background: Proven experience in cybersecurity and/or AI, with a strong interest in securing AI solutions. Previous experience in AI model development, adversarial testing, security assessments particularly within AI contexts, cybersecurity analytics is a plus.
• Client-Facing Experience: Strong interpersonal and communication skills, with experience in a consulting or client-facing role. Ability to translate complex technical findings into clear, actionable insights for diverse client audiences.
• Understanding of AI Security Threats: Familiarity with AI-specific vulnerabilities, such as model poisoning, prompt injections, and data obfuscation.
• Monitoring and Observability Skills: Hands-on experience with monitoring and observability platforms (e.g., Splunk, ELK Stack) is beneficial.
• Knowledge of Responsible AI Practices: Experience with explainable AI, fairness audits, and ethical AI practices.
• Analytical Skills: Strong ability to analyze security findings, conduct AI-driven threat assessments, and report insights effectively.
• Programming Skills: Proficiency in Python, with experience in AI/ML frameworks (e.g., TensorFlow, PyTorch) and cybersecurity tools (e.g., Metasploit, Nmap) preferred.
• Cloud Computing: Proficiency with cloud Frameworks (AWS, Azure), with a focus on securing machine learning workloads.

Preferred Qualifications:

• Certifications in security (e.g., CISSP, CEH, Security+) and/or relevant Cloud Computing certifications
• Understanding and expertise on the EU AI Act
• Familiarity with zero-trust architectures for AI systems.

Perks and Benefits:

• Opportunity to work with diverse clients across multiple industries.
• Competitive salary and performance bonuses.
• Choice of the hardware between MacBooks/Windows and iPhones/Android.
• Access to cutting-edge AI security technologies.
• Professional development and continuous learning opportunities.
• Flexible work arrangements.