New: upload your resume and get matched to AI jobs. Free to start →

Senior Staff Security Engineer, AI Safeguards - Moveworks

$201k - $352k • Mountain View, CALIFORNIA, United States • Full-time

Posted 7d ago

Job Location

Mountain View, CALIFORNIA, United States

Tech Stack

Remote Work Policy

On-site

Employment Type

Full-time

Categories

AI Engineer

About the job

Moveworks is seeking a Senior Staff Security Engineer to focus on AI Safeguards. This role involves maintaining a comprehensive understanding of ML usage and security measures across our products, and leading the security design for new ML features. You will be responsible for testing the limits of our safeguards against various attacks like jailbreaks and prompt injection, translating these findings into evaluation cases to ensure ongoing model and safeguard integrity. Additionally, you will collaborate with ML engineers to develop and implement robust mitigations, define key security metrics to assess safeguard effectiveness, and report on these metrics. The role also requires staying abreast of AI attack research, translating new techniques into practical tests and defenses, and reviewing changes that could compromise existing safeguards.

Responsibilities

  • Maintain and update the map of ML usage and safeguards across products.
  • Lead the security design for new ML features.
  • Test safeguards against attacks like jailbreaks, prompt injection, and toxicity.
  • Develop evaluation cases from test findings to run on all model and safeguard changes.
  • Design and build mitigations with ML engineers to address detection misses.
  • Define and report on security metrics for safeguard effectiveness.
  • Review changes that could weaken safeguards.
  • Track AI attack research and implement new techniques as tests and mitigations.

Requirements

  • 8+ years in security engineering, with 2+ years focused on AI or LLM security.
  • Hands-on adversarial experience (red teaming, penetration testing, vulnerability research) applied to LLM systems.
  • Deep knowledge of LLM attacks and defenses (e.g., OWASP Top 10 for LLM Applications, MITRE ATLAS).
  • Ability to identify risks, develop mitigation plans, and implement fixes.
  • Strong coding skills in Python or Go.
  • Proven record of shipping production code.
  • Sufficient ML fundamentals to build evals and judge classifier efficacy.

Benefits

  • Base pay: $201,300 - $352,300
  • Equity (when applicable)
  • Variable/incentive compensation
  • Health plans
  • Flexible spending accounts
  • 401(k) Plan with company match
  • ESPP
  • Matching donations
  • Flexible time away plan
  • Family leave programs

About ServiceNow