agent exploitation

**About the Role:** You’ll be the team’s continuous adversarial tester — not a final security review bolted on before launch, but an active role testing every safety-critical piece of the system as it’s built, throughout the entire 9-week build. Your written sign-off is the gate that has to be cleared before our AI agent is ever allowed to touch...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

Location: Remote Fluent Language Skills Required: English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs,...

We are a legal-intake advertising operation. We built an internal platform that watches every ad we run, transcribes it, breaks it into scenes, maps viewer retention onto those scenes, tags the creative on a structured genome (hook pattern, spokesperson, claim type, emotional arc, offer framing), and measures all of it against one number: cost per signed...

About The JobMercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey. Position: AI Safety Experts — English & Urdu Type: ContractCompensation: $20–$22/hourLocation:...