Senior Staff Security Engineer, AI Safeguards - Moveworks

Description

This is a senior staff security engineering role focused on AI safeguards.

The work covers how machine learning is used across the company's products and how those uses are protected.

Responsibilities

• Keep an up-to-date map of where machine learning is used in the products and which safeguards apply.
• Lead the security design of new machine learning features.
• Test safeguards against jailbreaks, prompt injection, prompt leaks and toxicity, then turn the findings into eval cases that run on every change to a model, prompt or safeguard.
• Build mitigations with ML engineers that still hold when detection misses an attack.
• Define the security metrics that show whether safeguards work, and report on them.
• Review changes that could weaken a safeguard.
• Follow AI attack research and turn new techniques into tests and mitigations.

Requirements

• Usually 8 or more years in security engineering, with 2 or more years focused on AI or LLM security.
• Hands-on adversarial experience, such as red teaming, penetration testing or vulnerability research, applied to LLM systems.
• Deep knowledge of LLM attacks and defenses, such as the OWASP Top 10 for LLM Applications and MITRE ATLAS.
• Able to assess risks, plan mitigations and implement the fixes yourself.
• Strong Python or Go skills, with a record of shipping production code and not only reporting findings.
• Enough ML fundamentals to write evals and judge how well a classifier performs.

Conditions

Work personas (flexible, remote, or required in office) are assigned based on the nature of the work and the employee's work location.

To confirm eligibility for a persona, the company may measure the distance between your primary residence and its closest office using a third-party service.