Senior Security Engineer, Agentic Red Team, DeepMind

Google DeepMind; Mountain View (CA); On-site; USD 180,000 - 230,000; Full time

Benefits offered by this job

Health Insurance

Stock Options

401k

Equity

Job summary

Google DeepMind is seeking a security-focused professional to conduct rapid assessments of agentic services in Generative AI. You will collaborate with product teams during design to identify vulnerabilities and maintain a library of agent-specific attack patterns.

The role requires a Bachelor's degree and 5+ years in Red Teaming or Offensive Security, with hands-on experience with Large Language Models and developing exploits for Generative AI models.

Qualifications

• Bachelor's degree in Computer Science or related field required, with 5+ years in Red Teaming or Offensive Security.
• Experience with Large Language Models and developing exploits for Generative AI models.

Responsibilities

• Conduct rapid security assessments on agentic services, focusing on vulnerabilities unique to Generative AI.
• Partner with developers during design phases to provide immediate feedback and maintain a library of agent-specific attack patterns.

Skills

Red Teaming

Offensive Security

Adversarial Machine Learning

Large Language Models

AI Vulnerability Classes

Exploits Development

Python

Go

C++

Security Tools

Automation

AI Safety Benchmarks

Fuzzing Techniques

Probabilistic Risks

Agentic Workflows

Tool Usage

Education

Bachelor's degree in Computer Science or related field

Job description

Conduct rapid security assessments on agentic services, focusing on vulnerabilities unique to Generative AI. Partner with developers during design phases to provide immediate feedback and maintain a library of agent-specific attack patterns.

Requirements: A bachelor's degree in Computer Science or related field is required, along with 5 years of experience in Red Teaming or Offensive Security. Candidates should have experience with Large Language Models and developing exploits for Generative AI models.

Key Skills: Red Teaming, Offensive Security, Adversarial Machine Learning, Large Language Models, AI Vulnerability Classes, Exploits Development, Python, Go, C++, Security Tools, Automation, AI Safety Benchmarks, Fuzzing Techniques, Probabilistic Risks, Agentic Workflows, Tool Usage

Benefits: Health Insurance, Stock Options, 401k, Equity