Remote AI Safety & Adversarial ML Specialist
San Francisco, San Francisco County, California, 94199, USA
Listed on 2026-10-11
-
IT/Tech
AI Evaluation, Data Annotation/ AI Labeling
Mercor is seeking AI Safety Experts for remote contract work. You will conduct red team testing on conversational AI models, focusing on jailbreaks, prompt injections, and misuse scenarios, while generating high-quality human data and reports.
You will annotate failures, classify vulnerabilities, and apply structured taxonomies to ensure consistent testing, documenting all findings for customer action.
We invite applications for the Remote AI Safety & Adversarial ML Specialist position located in San Francisco, CA, United States.
Our organisation is growing, and we are hiring a Remote AI Safety & Adversarial ML Specialist in San Francisco, CA, United States.
This opening is for the Remote AI Safety & Adversarial ML Specialist role at mercor.
We are seeking a motivated Remote AI Safety & Adversarial ML Specialist to join mercor in San Francisco, CA, United States.
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).