[EJV] Lead AI Safety & Security Engineer (with Joining Bonus)
Core
Lead AI Safety & Security Engineer responsible for safety evaluation, security testing, and threat modeling across Bosch's LLM and agentic AI systems.
Role type
Lead AI Safety & Security Engineer
Builds
Safety evaluation practices, security testing frameworks, and threat models for AI-enabled products and internal tooling.
Domain
Artificial Intelligence / Cybersecurity
Deliverable
production ML models | product features | dashboards & analysis | research | client delivery | infrastructure
Required skills
LLM safety evaluation, prompt injection testing, jailbreak testing, threat modeling, Python/JavaScript coding, technical writing, AI governance frameworks
Preferred skills
Model Context Protocol (MCP) experience, traditional penetration testing, AI governance program experience, open-source security tooling contributions
Technologies
Python, JavaScript, Node, MCP, OWASP Top 10 for LLM Applications, NIST AI RMF, ISO/IEC 42001, EU AI Act
Responsibilities
Design and run safety evaluations for LLM-based features and AI agents; Design and run security testing for agentic systems; Build and maintain threat models covering the full AI system path; Verify human-in-the-loop and guardrail controls; Scope and review external red-teaming/pentest vendor output; Track and apply emerging AI safety/security frameworks; Partner with AI/ML engineering teams to integrate safety/security into design; Produce evidence and documentation for AI governance and compliance; Build test tooling for adversarial prompts and tool schemas; Mentor engineers on safe and secure AI system design.
Seniority
Senior, hands-on IC with leadership responsibilities