LLM Adversarial Tester; Red Teamer; Remote

Handshake AI is seeking an AI Red Teamer (LLM Generalist) for remote engagement in the United States. You will design creative prompts to stress-test large language models, targeting safety, bias, guardrails, and resilience across text, image, and audio tasks as needed.

You will document experiments, score outputs with harm taxonomies, and collaborate with engineers and researchers to strengthen defenses. This contract role requires curiosity, ethical judgment, and the ability to work

Join us at Handshake as our next LLM Adversarial Tester (Red Teamer) - Remote in United States.

This is a genuine role to take on the LLM Adversarial Tester (Red Teamer) - Remote role at Handshake.

As a LLM Adversarial Tester (Red Teamer) - Remote, you will play an important part at Handshake in United States.