Remote Adversarial ML Specialist — AI Safety Red Team
Los Angeles, Los Angeles County, California, 94199, USA
Listed on 2026-10-20
-
IT/Tech
AI Evaluation, Data Annotation/ AI Labeling
Mercor is building a remote red team for AI safety. You will lead adversarial testing of conversational AI models, focusing on jailbreaks, prompt injections, misuse, and bias exploitation.
You will generate high-quality human data, annotate failures, classify vulnerabilities, and document findings in reproducible reports and datasets that help customers strengthen their AI systems. Ideal candidates bring prior red teaming experience, a curious adversarial mindset, structured approaches, and the
For the Remote Adversarial ML Specialist — AI Safety Red Team position at Obsidian, we are reviewing applications now.
Join Obsidian and contribute to our ongoing work.
Take a moment to read everything above and see whether this role is right for you.
This posting is for the Remote Adversarial ML Specialist — AI Safety Red Team role at Obsidian, based 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).