Lead AI Safeguards Engineer

VulnU; Mountain View (CA); On-site; USD 200,000 - 280,000; Full time

Benefits offered by this job

Paid parental leave

Retirement match

Equity

Learning budget

Job summary

Moveworks is seeking a Senior Staff Security Engineer for AI Safeguards to design and secure ML features across our platform. You will drive safeguards, run adversarial testing, and convert findings into robust evals that run as the model and safeguards evolve.

Expect hands-on security work with Python/Go, strong ML fundamentals, and the ability to quantify safeguards performance and risk. This role anchors Moveworks security in a rapidly advancing AI landscape.

Qualifications

• 8+ years in security engineering, including 2+ years focused on AI/LLM security.
• Hands-on adversarial experience, e.g., red teaming or penetration testing in LLM systems.
• Deep knowledge of LLM attacks and defenses, including OWASP Top 10 for LLM apps.
• Strong coding skills in Python or Go with production-grade code delivery.
• Ability to identify risks, craft mitigations, and drive fixes end-to-end.
• ML fundamentals to build evals and judge classifier efficacy.

Responsibilities

• Keep the map of ML usage and safeguards across our products current.
• Lead the security design of new ML features and safeguards.
• Break our safeguards: test jailbreaks, prompt injection, prompt leaks and toxicity.
• Turn findings into eval cases that run on every model, prompt and safeguard change.
• Define security metrics and report on them to stakeholders.
• Review changes that could weaken a safeguard and propose fixes.
• Track AI attack research and turn new techniques into tests and mitigations.

Skills

Security engineering

AI/LLM security

Red teaming

Penetration testing

Python

Go

Adversarial testing

Threat modeling

Job description

Moveworks is seeking a Senior Staff Security Engineer for AI Safeguards to design and secure ML features across our platform. You will drive safeguards, run adversarial testing, and convert findings into robust evals that run as the model and safeguards evolve.

Expect hands-on security work with Python/Go, strong ML fundamentals, and the ability to quantify safeguards performance and risk. This role anchors Moveworks security in a rapidly advancing AI landscape.