Lakera
Senior Research Engineer - Security Foundation Models(m/w/x)
Full-timeOn-siteSenior
Zürich
New Job?Nejo!
The AI Job Search Engine
DEDeepMind
Senior Security Engineer, Agentic Red Team(m/w/x)
Zürich
from USD 166,000 - 244,000 / year
Full-timeOn-siteSenior
AI/ML
Nejo AI Summary
Red teaming agentic services and production AI models for scientific discovery, engineering exploits. Experience developing exploits for GenAI models required. Focus on state-of-the-art AI security challenges.
Requirements
- Bachelor's degree in Computer Science, Information Security, or equivalent practical experience
- Experience in Red Teaming, Offensive Security, or Adversarial Machine Learning
- Strong coding skills (Python, Go, C++) and security tool/automation experience
- Technical understanding of LLM architectures, agentic workflows, and AI vulnerability classes
- Hands-on experience developing GenAI model exploits
- Consulting experience with product teams or startup-like environment
- Familiarity with AI safety benchmarks, evaluation frameworks, and fuzzing
- Translation of complex probabilistic risks to engineering fixes
Tasks
- Conduct rapid security assessments on agentic services
- Identify GenAI vulnerabilities (e.g., prompt injection)
- Uncover tool-use escalation and lateral movement flaws
- Engineer and execute complex attack sequences
- Exploit non-deterministic model behaviors
- Exploit agentic logic errors and data poisoning
- Develop automated regression testing frameworks
- Transform manual discoveries into Auto Red Teaming
- Prevent regression in future model versions
- Partner with developers during design and build
- Provide immediate feedback to product teams
- Shorten feedback loops for defensive engineering
- Maintain and expand a library of attack patterns
- Curate agent-specific exploit primitives
- Establish robust release criteria for new models
- Codify findings into reusable guardrails
Work Experience
- approx. 4 - 6 years
Education
- Bachelor's degree
Languages
- English – Business Fluent
Tools & Technologies
- Python
- Go
- C++
Benefits
Bonuses & Incentives
- Bonus
Competitive Pay
- Equity
Other Benefits
- Disability accommodation
Find the original job posting in its most current version here. Nejo automatically captured this job from the website of DeepMind and processed the information on Nejo with the help of AI for you. Despite careful analysis, some information may be incomplete or inaccurate. Please always verify all details in the original posting! Content and copyrights of the original posting belong to the advertising company.
Not a perfect match?
- Anthropic
Senior Security Software Engineer, eBPF & Security Sensors(m/w/x)
Full-timeWith HomeofficeSeniorZürichfrom CHF 280,000 - 350,000 / year - Scopely
Senior Security Engineer - Software Security(m/w/x)
Full-timeOn-siteSeniorZürich - Snap Inc
Security Engineer(m/w/x)
Full-timeOn-siteExperiencedZürich - Anthropic
Engineering Manager, Detection and Response(m/w/x)
Full-timeOn-siteSeniorZürich
DEDeepMind
Senior Security Engineer, Agentic Red Team(m/w/x)
Zürich
from USD 166,000 - 244,000 / year
Full-timeOn-siteSenior
AI/ML
Nejo AI Summary
Red teaming agentic services and production AI models for scientific discovery, engineering exploits. Experience developing exploits for GenAI models required. Focus on state-of-the-art AI security challenges.
Requirements
- Bachelor's degree in Computer Science, Information Security, or equivalent practical experience
- Experience in Red Teaming, Offensive Security, or Adversarial Machine Learning
- Strong coding skills (Python, Go, C++) and security tool/automation experience
- Technical understanding of LLM architectures, agentic workflows, and AI vulnerability classes
- Hands-on experience developing GenAI model exploits
- Consulting experience with product teams or startup-like environment
- Familiarity with AI safety benchmarks, evaluation frameworks, and fuzzing
- Translation of complex probabilistic risks to engineering fixes
Tasks
- Conduct rapid security assessments on agentic services
- Identify GenAI vulnerabilities (e.g., prompt injection)
- Uncover tool-use escalation and lateral movement flaws
- Engineer and execute complex attack sequences
- Exploit non-deterministic model behaviors
- Exploit agentic logic errors and data poisoning
- Develop automated regression testing frameworks
- Transform manual discoveries into Auto Red Teaming
- Prevent regression in future model versions
- Partner with developers during design and build
- Provide immediate feedback to product teams
- Shorten feedback loops for defensive engineering
- Maintain and expand a library of attack patterns
- Curate agent-specific exploit primitives
- Establish robust release criteria for new models
- Codify findings into reusable guardrails
Work Experience
- approx. 4 - 6 years
Education
- Bachelor's degree
Languages
- English – Business Fluent
Tools & Technologies
- Python
- Go
- C++
Benefits
Bonuses & Incentives
- Bonus
Competitive Pay
- Equity
Other Benefits
- Disability accommodation
Find the original job posting in its most current version here. Nejo automatically captured this job from the website of DeepMind and processed the information on Nejo with the help of AI for you. Despite careful analysis, some information may be incomplete or inaccurate. Please always verify all details in the original posting! Content and copyrights of the original posting belong to the advertising company.
About the Company
DeepMind
Industry
Science
Description
The company advances the state of the art in artificial intelligence for public benefit and scientific discovery.
Not a perfect match?
- Lakera
Senior Research Engineer - Security Foundation Models(m/w/x)
Full-timeOn-siteSeniorZürich - Anthropic
Senior Security Software Engineer, eBPF & Security Sensors(m/w/x)
Full-timeWith HomeofficeSeniorZürichfrom CHF 280,000 - 350,000 / year - Scopely
Senior Security Engineer - Software Security(m/w/x)
Full-timeOn-siteSeniorZürich - Snap Inc
Security Engineer(m/w/x)
Full-timeOn-siteExperiencedZürich - Anthropic
Engineering Manager, Detection and Response(m/w/x)
Full-timeOn-siteSeniorZürich