[EJV] Lead AI Security Engineer (LLM & Agentic AI) - with Joining Bonus
Bosch Global25 days ago
Ho Chi Minh City, VietnamStaff+
Responsibilities
- Design and run safety evaluations for LLM features and AI agents, including harmful-output, bias, jailbreak, guardrail-bypass, and safety-failure testing.
- Perform security testing for prompt injection, excessive agency, tool/plugin abuse, confused-deputy risks, and MCP-style tool-calling architectures.
- Build threat models spanning user input, model reasoning, and tool execution, and assess human-in-the-loop and guardrail controls.
- Scope, brief, and review external red-teaming and penetration-testing engagements, including test specifications and acceptance criteria.
- Track OWASP, NIST AI RMF, ISO/IEC 42001, and EU AI Act developments and convert them into internal engineering requirements.
- Partner with AI/ML engineering teams to integrate safety and security reviews into system design.
- Produce AI governance and compliance evidence and documentation.
- Build adversarial-prompt harnesses, automated jailbreak and red-team pipelines, and MCP/tool-schema fuzzers.
- Mentor engineers and establish the AI safety and security testing practice across business units.
Requirements
- Bachelor’s or master’s degree in Computer Science, Machine Learning, or a related field.
- At least 6 years of experience in security testing.
- At least 2 years of AI/ML safety research or closely related experience with demonstrated real-world findings.
- At least 2 years of practical LLM or agentic AI testing or red-teaming experience, with independent research or open-source contributions accepted.
- Working knowledge of at least one AI safety or governance framework, including NIST AI RMF, ISO/IEC 42001, or the EU AI Act.
- Coding ability in Python and/or JavaScript/Node for building evaluation harnesses and testing tools.
- Strong technical writing skills for producing actionable findings and specifications.
- Preferred qualifications include MCP or comparable agent tool-calling experience, traditional web/API/network penetration testing, OSCP or equivalent, AI governance experience, relevant publications or open-source security tooling, and experience mentoring or building a safety/security testing team.
- Relevant certifications include OSCP, OSWE, OSEP, GPEN, GWAPT, CEH, ISC2 AI Security Certificate, EC-Council Certified Offensive AI Security Professional, CAISP, ISO/IEC 42001 Lead Auditor or Lead Implementer, and IAPP AIGP.
Benefits
- Joining bonus equivalent to one month’s gross salary for eligible employees joining by 31 December 2026.
- 13th-month salary bonus, performance bonus, and annual performance appraisal.
- 100% offered salary and mandatory social insurance during the 2-month probation period.
- More than 15 days of annual leave plus one birthday leave day.
- Premium health insurance for the employee and two family members.
- Flexible working time and working model.
- Lunch and parking allowances.
- English-speaking environment, global projects, innovation opportunities, training programs, and short- and long-term assignments at worldwide offices.
- Company activities including football, badminton, yoga, aerobics, and team building.
Tech Stack
Categories
About Bosch Global
Bosch Global (Robert Bosch GmbH) develops and sells mobility components and software, industrial automation and sensors, home appliances and power tools, and energy and building technologies to automakers, manufacturers, builders, and consumers. It monetizes through product sales and connected services spanning IoT, AI, and embedded software. Founded in 1886 and headquartered in Gerlingen-Schillerhöhe, Germany, the privately held Bosch Group operates worldwide across Mobility, Industrial Technology, Consumer Goods, and Energy and Building Technology sectors.