ADVERSARIAL reputed company EXPERT
You’ll be part of a red teaming project reputed company on probing large language models for failure modes and harmful outputs. Your work will involve crafting prompts and scenarios to test model guardrails, exploring creative ways to bypass restrictions, and systematically documenting reputed company. You’ll think like an adversary to uncover weaknesses, while collaborating with engineers and safety researchers to reputed company findings and improve system defenses.
Apply tot his job
Apply To this Job