The AI Job Search Engine
Senior Security Engineer, Agentic Red Team(m/w/x)
Description
You will lead adversarial engagements by embedding with product teams to identify flaws and execute complex attacks on AI models, ultimately codifying your findings into automated defenses.
Let AI find the perfect jobs for you!
Upload your CV and Nejo AI will find matching job offers for you.
Requirements
- •Degree in Computer Science or equivalent
- •Experience in Red Teaming or Offensive Security
- •Strong coding skills in Python, Go, or C++
- •Understanding of LLM architectures and AI vulnerabilities
- •Experience developing exploits for GenAI models
- •Experience in consulting or startup environments
- •Familiarity with AI safety benchmarks and fuzzing
- •Ability to translate risks into engineering fixes
Education
Work Experience
approx. 4 - 6 years
Tasks
- •Execute rapid security assessments on agentic services
- •Identify architectural flaws during the design phase
- •Perform multi-turn attacks on production AI models
- •Target vulnerabilities like prompt injection and tool-use escalation
- •Engineer exploits for non-deterministic model behaviors
- •Develop automated regression testing frameworks
- •Partner with developers to provide immediate security feedback
- •Maintain a library of agent-specific attack patterns
Tools & Technologies
Languages
English – Business Fluent
Benefits
Bonuses & Incentives
- •Bonus
Competitive Pay
- •Equity
Other Benefits
- •Disability accommodation
- LakeraFull-timeOn-siteSeniorZürich
- Scopely
Senior Security Engineer - Software Security(m/w/x)
Full-timeOn-siteSeniorZürich - RepRisk AG
Senior AI Engineer(m/w/x)
Full-timeOn-siteSeniorZürich - Lakera
Research Internship(m/w/x)
Full-timeInternshipOn-siteZürich - Lakera
Director of Engineering, Detectors Group(m/w/x)
Full-timeOn-siteSeniorZürich
Senior Security Engineer, Agentic Red Team(m/w/x)
The AI Job Search Engine
Description
You will lead adversarial engagements by embedding with product teams to identify flaws and execute complex attacks on AI models, ultimately codifying your findings into automated defenses.
Let AI find the perfect jobs for you!
Upload your CV and Nejo AI will find matching job offers for you.
Requirements
- •Degree in Computer Science or equivalent
- •Experience in Red Teaming or Offensive Security
- •Strong coding skills in Python, Go, or C++
- •Understanding of LLM architectures and AI vulnerabilities
- •Experience developing exploits for GenAI models
- •Experience in consulting or startup environments
- •Familiarity with AI safety benchmarks and fuzzing
- •Ability to translate risks into engineering fixes
Education
Work Experience
approx. 4 - 6 years
Tasks
- •Execute rapid security assessments on agentic services
- •Identify architectural flaws during the design phase
- •Perform multi-turn attacks on production AI models
- •Target vulnerabilities like prompt injection and tool-use escalation
- •Engineer exploits for non-deterministic model behaviors
- •Develop automated regression testing frameworks
- •Partner with developers to provide immediate security feedback
- •Maintain a library of agent-specific attack patterns
Tools & Technologies
Languages
English – Business Fluent
Benefits
Bonuses & Incentives
- •Bonus
Competitive Pay
- •Equity
Other Benefits
- •Disability accommodation
About the Company
DeepMind
Industry
Science
Description
The company advances the state of the art in artificial intelligence for public benefit and scientific discovery.
- Lakera
Senior Research Engineer - Security Foundation Models(m/w/x)
Full-timeOn-siteSeniorZürich - Scopely
Senior Security Engineer - Software Security(m/w/x)
Full-timeOn-siteSeniorZürich - RepRisk AG
Senior AI Engineer(m/w/x)
Full-timeOn-siteSeniorZürich - Lakera
Research Internship(m/w/x)
Full-timeInternshipOn-siteZürich - Lakera
Director of Engineering, Detectors Group(m/w/x)
Full-timeOn-siteSeniorZürich