Note: The job is a remote job and is open to candidates in USA. Nebius Academy, powered by TripleTen, partners with companies to help technical teams adopt AI safely and build practical, job-ready skills. The role delivers hands-on AI Security workshops for experienced engineering teams, demonstrating attacks and mitigations involving agentic AI, MCP, AI-generated code, supply-chain risks, and data governance. The instructor also reviews client security configurations and collaborates on refining workshop materials and labs.
Responsibilities
- Deliver hands-on AI Security workshops for experienced engineering teams, combining concise concept explanations with practical labs on real repositories
- Demonstrate real-world attack scenarios and mitigations involving agentic AI coding tools, including indirect prompt injection, delegated permissions, autonomous command execution, and workspace trust
- Guide learners through MCP security practices, including trust boundaries, read/write scoping, least-privilege configurations, and re-approval of changed tool definitions
- Help engineers secure AI-generated code and pull requests using DevSecOps controls such as secret scanning, SAST, SCA, branch protection, CODEOWNERS, and repository-level security instructions
- Explain and demonstrate AI-specific supply-chain risks, including hallucinated dependencies, poisoned tool descriptions, and compromised MCP servers
- Facilitate practical discussions around AI data governance, including sensitive data exposure, credentials, proprietary code, model data flows, retention, and content exclusions
- Review the client's AI tooling configuration and existing security controls ahead of workshops to tailor examples and exercises to their environment
- Collaborate with the Nebius Academy team and subject-matter experts to refine workshop materials, labs, and security practices based on learner needs and evolving AI security risks
Skills
- * Strong hands-on experience in **AI Security**, with practical understanding of security risks introduced by agentic AI systems and AI-assisted engineering workflows
- * Deep understanding of the **agentic AI attack surface**, including indirect and persistent prompt injection, delegated authority, blast radius, approval flows, workspace trust, and autonomous command execution
- * Practical knowledge of **MCP security and trust boundaries**, including read/write scoping, least-privilege configuration, permissions, and tool re-approval
- * Hands-on experience with **GitHub Copilot, VS Code, and Python**, sufficient to demonstrate realistic attacks and mitigations live
- * Strong understanding of **DevSecOps controls for AI-generated code**, including secret scanning, SAST, SCA, branch protection, CODEOWNERS, and secure repository practices
- * Knowledge of **AI-specific supply-chain risks**, such as hallucinated dependencies, poisoned tool descriptions, and compromised MCP servers
- * Experience delivering technical workshops, facilitating engineering groups, or leading practical knowledge-sharing sessions for experienced technical audiences
- * Professional fluency in English
- * Experience working in regulated environments such as **insurance, finance, or healthcare**
- * Familiarity with frameworks and standards such as **OWASP Agentic Top 10, OWASP MCP Top 10, NIST AI RMF, ISO 42001, or the EU AI Act**
- * Experience with AI security audit trails, incident response, injection testing, or guardrail regression testing
- * Experience creating AI usage policies, security checklists, or other practical security guidance for engineering teams
Benefits
- The opportunity to share your expertise while maintaining your primary job: Deliver high-impact AI Security workshops without leaving your current role.
- Remote cooperation with a schedule convenient for both you and the team: We can work with experts across different locations and time zones.
- Work with experienced engineering audiences: Help technical professionals understand and mitigate real-world security risks introduced by agentic AI systems.
- Meaningful impact: Contribute to practical AI Security education in an area with rapidly growing demand from enterprise clients.
- Participation in innovative projects: Work on hands-on workshops around agentic AI security, MCP, AI supply-chain risks, secure coding workflows, and related emerging practices.
- Potential for continued collaboration: Strong experts may be invited to contribute to future AI Security workshops, courses, and learning content beyond the initial engagement.
Company Overview