AI Safety Engineer: Anti-Abuse & Trust Systems

Zizy Inc.; New York, Northern (NY, KY); Hybrid; USD 120,000 - 170,000; Full time

Benefits offered by this job

Mental health and wellness support

Generous time off policy

Paid parental leave and family-planing

Annual learning & development stipend

Job summary

Zizy Inc. is seeking a software engineer to help us build trust and safety capabilities across our AI platform. You will design and implement systems to detect and prevent abuse, promote user safety, and reduce risk.

You will collaborate with engineers and researchers, using both standard and novel AI techniques to combat abuse and protect end users. You will own end-to-end projects from design through deployment with a focus on responsible AI safety.

Qualifications

• At least 3 years of professional software engineering experience.
• Experience setting up and maintaining production backend services and data pipelines.
• Interest in AI safety in production environments and the ability to defend against abuse.
• Ability to own problems end-to-end and learn as needed to get the job done.

Responsibilities

• Architect, build, and maintain anti-abuse and content moderation infrastructure.
• Collaborate with engineers and researchers to apply AI techniques to combat abuse and toxic content.
• Assist with incident response and build tooling to address core security and safety challenges.

Skills

Software engineering

Self-directed

Team collaboration

Problem solving

Ownership

Tools

Terraform

Kubernetes

Azure

Python

Postgres

Kafka

Job description

Zizy Inc. is seeking a software engineer to help us build trust and safety capabilities across our AI platform. You will design and implement systems to detect and prevent abuse, promote user safety, and reduce risk.

You will collaborate with engineers and researchers, using both standard and novel AI techniques to combat abuse and protect end users. You will own end-to-end projects from design through deployment with a focus on responsible AI safety.