Platform Engineer III

Job Summary

We are seeking a Vision AI Security Engineer to ensure the security, resilience, and trustworthiness of the VisionX platform, including computer vision solutions, AI/ML models, video analytics pipelines, and GenAI-powered capabilities. The ideal candidate will combine expertise in cybersecurity, AI security, and secure software engineering to identify, assess, and mitigate vulnerabilities, adversarial threats, model risks, and misuse scenarios across the end-to-end AI ecosystem.

Key Responsibilities

Own end-to-end security for Vision AI platforms, covering UI, APIs, microservices, workflows, integrations, AI models, and cloud deployments.Define and implement AI security strategies, threat models, risk assessments, security policies, and release security sign-off criteria.Perform security assessments, vulnerability analysis, and penetration testing across applications, APIs, infrastructure, cloud environments, and AI workloads.Evaluate application and API security controls, including authentication, authorization, RBAC, token management, secrets handling, and injection prevention mechanisms.Identify and mitigate AI-specific threats, including adversarial attacks, prompt injection, jailbreak attempts, model evasion, data poisoning, model theft, and sensitive data exposure.Assess and secure GenAI/LLM solutions, ensuring robust prompt handling, secure tool/function calling, data protection, and misuse prevention controls.Review and validate the security of RAG architectures, including content ingestion, retrieval boundaries, grounding integrity, source trustworthiness, and data access controls.Ensure secure handling of sensitive and regulated data, including privacy controls, PII protection, encryption, and compliance requirements across AI pipelines.Assess the security posture of computer vision and video analytics solutions, including image/video ingestion pipelines, inference services, edge deployments, and connected devices.Drive application security testing using SAST, DAST, SCA, container, and cloud security assessment tools; prioritize findings and support remediation validation.Integrate automated security validation into CI/CD pipelines to enable continuous security monitoring and DevSecOps practices.Conduct red-team exercises, attack simulations, abuse-case testing, and adversarial AI assessments to evaluate platform resilience against emerging threats.Validate security-related operational controls, including rate limiting, throttling, API protection, monitoring, logging, and incident response readiness.Lead security issue triage, root-cause analysis, risk reporting, and compliance activities across the Vision AI ecosystem.Collaborate with architects, engineering, MLOps, and DevOps teams to implement secure-by-design principles and effective mitigation strategies throughout the AI solution lifecycle.Ensure Vision AI solutions meet security, privacy, regulatory, and production-readiness standards before deployment.

Skill Requirements

Strong knowledge of application security, secure SDLC, threat modeling, vulnerability management, and security-by-design principles.Hands-on experience with application security assessment tools such as OWASP ZAP, Burp Suite, SonarQube, SAST, DAST, SCA, and other enterprise security platforms.Deep understanding of OWASP Top 10, API Security Top 10, authentication and authorization frameworks (OAuth2, JWT, SSO, RBAC), and access control mechanisms.Proven experience securing web applications, APIs, cloud-native solutions, microservices, and enterprise integrations using modern security frameworks and best practices.Proficiency in Python scripting and security automation to enable scalable security validation, monitoring, and DevSecOps implementations.Strong understanding of AI/ML architectures, model lifecycles, data pipelines, and security considerations across AI-powered systems.Experience securing GenAI and LLM-based applications, including protection against prompt injection, jailbreak attacks, unsafe outputs, model abuse, and data leakage risks.Knowledge of RAG security principles, including grounding integrity, retrieval controls, source trust validation, vector database security, and prevention of unauthorized data exposure.Understanding of AI-specific threat models, including adversarial attacks, data poisoning, model evasion, model theft, and privacy-related risks.Experience assessing the security of computer vision and video analytics solutions, including image/video ingestion pipelines, inference services, edge AI deployments, and connected devices.Familiarity with cloud security concepts across Azure, AWS, or GCP, including IAM, network security, secrets management, container security, and workload protection.Strong knowledge of security monitoring, incident response, risk assessment, compliance, and governance frameworks relevant to AI and enterprise applications.

Other Requirements

null