[EJV] Lead AI Safety & Security Engineer
Core
Lead the design and execution of safety evaluations and security testing for Bosch's AI-enabled products, including LLM deployments and agentic AI systems with tool-calling integrations.
Role type
Lead AI Safety & Security Engineer
Builds
Safety evaluation practices, security testing pipelines, threat models, and compliance documentation for AI systems.
Domain
Artificial Intelligence / Cybersecurity / Enterprise Software
Deliverable
production ML models | product features | dashboards & analysis
Required skills
LLM safety evaluation, prompt injection testing, jailbreak detection, threat modeling, Python/JavaScript coding, technical writing, AI governance frameworks (NIST, ISO/IEC 42001, EU AI Act)
Preferred skills
Model Context Protocol (MCP) experience, traditional penetration testing, AI governance program contribution, open-source security tooling, team mentoring
Technologies
Python, JavaScript/Node, MCP, OWASP Top 10 for LLM/Agentic Applications, NIST AI RMF, ISO/IEC 42001
Responsibilities
Design and run red-teaming and security testing for LLMs and AI agents; build threat models covering user input to tool execution; verify human-in-the-loop controls; scope external vendor engagements; apply emerging AI safety/security frameworks; partner with engineering teams on secure design; build automated test tooling; mentor engineers on safe AI design.
Seniority
Senior, hands-on IC with leadership responsibilities