Lead AI Safety & Security Engineer at Bosch

Confirmed open

Bosch is recruiting for the Lead AI Safety & Security Engineer role in Ho Chi Minh city, Vietnam. The work includes design and run safety evaluations for LLM-based features and AI agents: red-teaming for harmful, biased, or.

Bosch

Location: Ho Chi Minh city, Vietnam
Employment: Full-time
Technologies: Python, JavaScript

Role overview

We are looking for a Lead AI Safety & Security Engineer to own safety evaluation and security testing across Bosch's growing portfolio of AI-enabled products and internal tooling — large language model deployments and agentic AI systems (including Model Context Protocol – style tool-calling integrations), and the enterprise services they connect to. You will lead both sides of the same coin: whether an AI system behaves safely (does it refuse harmful requests, avoid unsafe recommendations, stay within its intended scope) and whether it is secure (can it be manipulated via prompt injection, tricked into misusing its tools, or made to leak data it shouldn't). This is a cross-business-unit mandate, not a single product line — you will build the practice largely from the ground up.

Key Responsibilities.

Responsibilities

Design and run safety evaluations for LLM-based features and AI agents: red-teaming for harmful, biased, or unsafe outputs; jailbreak and guardrail-bypass testing; systematic benchmarking against known safety failure modes.
Design and run security testing for the same systems: prompt injection (direct and indirect), excessive agency, tool/plugin abuse, and confused-deputy risks in agentic and MCP-style tool-calling architectures.
Build and maintain a threat model covering the full path from user input through model reasoning to tool execution — identifying where a safety failure and a security failure are really the same underlying gap.
Verify human-in-the-loop and guardrail controls are architecturally sound wherever an AI agent can take a consequential action (a write to a business system, an automated communication, a code change) — not just present in a UI that can be talked around.
Scope, brief, and review the output of external red-teaming/pentest vendors; write test specifications and acceptance criteria for AI-specific engagements.
Track and apply emerging frameworks — OWASP Top 10 for LLM Applications, OWASP Top 10 for Agentic Applications, the NIST AI Risk Management Framework, ISO/IEC 42001, and the EU AI Act — translating new research into concrete internal test requirements before it becomes an incident.
Partner with AI/ML engineering teams across business units to get safety and security reviewed into system design, not only tested after the fact.
Produce evidence and documentation supporting AI governance and compliance needs (ISO/IEC 42001 AI management system, EU AI Act risk assessments, internal responsible-AI review processes).
Build test tooling as needed: adversarial-prompt harnesses, automated jailbreak/red-team pipelines, and MCP/tool-schema fuzzers.
Mentor engineers on safe and secure AI system design, and grow the practice as it scales across more teams and products.

Qualifications

Required Qualifications.
Preferred Qualifications.
Relevant Certifications (any of the following a plus).
Bachelor's or Master's degree in Computer Science, Machine Learning, or a related field.
6+ years in security testing, AI/ML safety research, or a closely related discipline, with a track record of finding real issues in real systems.
Practical experience testing or red-teaming LLM/agentic AI systems — prompt injection, jailbreaks, excessive agency, tool/plugin abuse — independent research or open-source contributions are acceptable given how new this specialty is.
Working Understanding of at least one AI safety/governance framework (NIST AI RMF, ISO/IEC 42001, EU AI Act) and how it translates into concrete engineering requirements.
Enough coding ability (Python and/or JavaScript/Node) to build evaluation harnesses and test tooling rather than rely solely on manual testing.
Strong technical writing — comfortable producing findings and specifications that both engineers and governance/compliance stakeholders can act on directly.
Direct experience in the Model Context Protocol (MCP) or comparable agent tool-calling frameworks.
Traditional penetration testing background (web/API/network), OSCP or equivalent.
Experience contributing to a formal AI governance or compliance program.
Publications, CTF/red-team competition results, or open-source security tooling in the AI safety/security space.
Experience mentoring or building out a small safety/security testing team.
Offensive security / penetration testing — OSCP, OSWE, OSEP, GPEN, GWAPT, or CEH.
AI-specific security — ISC2 AI Security Certificate, EC-Council Certified Offensive AI Security Professional, or Certified AI Security Professional (CAISP).
AI governance / compliance — ISO/IEC 42001 Lead Auditor or Lead Implementer, or IAPP AI Governance Professional (AIGP).

Benefits

Join in a dynamic and fast-growing global company ( English-speaking environment), with opportunity to work in global projects and being a part of innovation team contributing initiative ideas to the hi-tech world.
Onsite opportunities: short-term and long-term assignments in worldwide offices.
Engage in our diverse training programs which surely help strengthen both your personal and professionalism.
13th-month salary bonus + attractive performance bonus (you'll love it!) + annual performance appraisal.
100% offered salary and mandatory social insurances in 2-month probation.
more than 15 days of annual leave + 1-day of birthday leave.
Premium health insurance for employee and 02 family members.
Flexible working time and working model.
Lunch and parking allowance.
Good benefits of company activities such as: football, badminton, yoga, Aerobic, team building….

About Bosch

Bosch Global Software Technologies develops engineering and software solutions within the Bosch Group. Its Vietnam development centre is based in Ho Chi Minh City and works with international teams.

How to apply

Review the original posting and apply through the employer’s careers page.

View source and apply

Source checked: 2026-09-25

Browse job categories

Python