Company
We partner with enterprises to advise, build, and secure AI systems.
Our focus is on developing AI and Generative AI solutions while managing the security, governance, and operational risks that come with deploying AI at enterprise scale.
Job Description
As a Senior AI Security Engineer, you will be crucial in safeguarding our advanced AI models, data, and infrastructure. You'll work closely with Data Scientists, Data Engineers, and MLOps / DevOps teams.
Additional responsibilities include :
- Implement defenses against AI-specific attacks (adversarial, prompt injection, data leakage)
- Conduct AI-focused security assessments, penetration tests, red / purple team exercises
- Analyze AI system vulnerabilities, develop mitigation strategies, and create AI risk heat maps
- Implement security controls throughout the AI / ML lifecycle (data handling, training with GPU isolation, deployment, monitoring, versioning, provenance). Integrate SAST / DAST for ML artifacts
- Manage audit trails and automated compliance checks
- Implement AI-specific incident response and develop regulatory disclosure playbooks
- Manage AI security monitoring, implement executive dashboards linking security to business KPIs, develop security metrics (Adversarial Risk Score, Model Drift Index)
- Implement secure training environments and fine-grained data access controls
- Contribute to AI-generated fraud detection in transaction monitoring systems.
- Act as an AI security SME, continuously research emerging threats
Qualifications
Required
Bachelor's degree in computer science, Engineering, or a related field.3-5+ years of experience in cybersecurity (application, cloud and data security) with strong proficiency in security scripting, automation, and tool development.Deep understanding of AI-specific threat vectors (adversarial attacks, prompt injection, data leakage).Demonstrated, hands-on experience with the Azure or AWS Cloud ecosystem and its security services.Proven experience translating regulatory frameworks (NIST AI RMF, EU AI Act) into technical controls.Preferred
Knowledge of AI security frameworks.Azure Cloud security services ecosystem (Microsoft Sentinel, Azure Monitor, Azure Policy, Purview, Key Vault, Azure ML security).Securing MLOps / LLMOps pipelines (data versioning, provenance, GPU isolation).Security frameworks (OWASP AI Security & Privacy Guide).Automated compliance checks (e.g., via Azure Monitor).Security monitoring (e.g., Microsoft Sentinel with KQL).Secure training environments (Azure ML, HSMs).Data access controls (Azure Policy, Purview).Security assessment tools (SAST, DAST) adapted for ML.Familiarity with relevant data privacy and security regulations (GDPR, DORA).