AI Safety Evaluations & Red Teaming Intern

Meta; Menlo Park (CA); Vor Ort; USD 30.000 - 34.000; Vollzeit

Zusammenfassung

Meta's Safety Evals and Red Teaming team within Products and Applied Research is seeking Research Interns for a 16-week program in Menlo Park, CA. Interns will explore areas such as agent safety, benchmarks, synthetic data generation, automated red teaming, LLM-as-a-Judge, benchmark design, eval harnesses, and prompt injection across several start dates throughout the year.

Ideal candidates are passionate about evaluating AI safety, designing experiments, and collaborating with cross-functional

Aufgaben

• How reliably do LLM-based judges identify safety-policy violations across different tasks, prompts, and adversarial conditions?
• How should we evaluate prompt-injection risks when an agent interacts with tools and untrusted information? Which environments and attack scenarios expose failures that simpler tests miss?
• Which automated red teaming methods uncover meaningful safety failures, and how well do those failures generalize beyond the prompts or environments used to find them?
• How can we use synthetic data and benchmark design to improve coverage while checking that scores reflect the behavior we intend to measure?

Jobbeschreibung

Meta's Safety Evals and Red Teaming team within Products and Applied Research is seeking Research Interns for a 16-week program in Menlo Park, CA. Interns will explore areas such as agent safety, benchmarks, synthetic data generation, automated red teaming, LLM-as-a-Judge, benchmark design, eval harnesses, and prompt injection across several start dates throughout the year.

Ideal candidates are passionate about evaluating AI safety, designing experiments, and collaborating with cross-functional