AI Safety & Abuse Detection Engineer

OpenAI; California (MO); On-site; USD 180,000 - 240,000; Full time

Job summary

OpenAI seeks a Protection Scientist Engineer within the Integrity team to design and build systems that proactively identify and enforce against abuse on OpenAI’s products. You will monitor new launches, sustain ongoing monitoring, and prototype scalable defenses, while handling critical escalations with cross-functional teams.

You will work with Product, Policy, Ops, and Investigative groups, leverage SQL and Python for technical analysis, and participate in on-call rotations, potentially

Qualifications

• 4+ years of experience in technical analysis and detection.
• Experience with SQL and Python for data-driven investigations.
• Familiarity with trust and safety, enforcement, and working with policy teams.

Responsibilities

• Scope and implement abuse monitoring requirements for new product launches.
• Improve processes to sustain monitoring operations for existing products.
• Prototype and mature production systems for detection, review, and enforcement of abuse.
• Collaborate with Product, Policy, Ops, Investigative, and Engineering teams to address risks.

Skills

SQL

Python

Technical analysis

Trust and safety collaboration

Data pipelines

ML concepts

Job description

OpenAI seeks a Protection Scientist Engineer within the Integrity team to design and build systems that proactively identify and enforce against abuse on OpenAI’s products. You will monitor new launches, sustain ongoing monitoring, and prototype scalable defenses, while handling critical escalations with cross-functional teams.

You will work with Product, Policy, Ops, and Investigative groups, leverage SQL and Python for technical analysis, and participate in on-call rotations, potentially