Research Scientist Intern - PAR Safety Evals and Red Teaming

Meta; Menlo Park (CA); On-site; USD 30,000 - 34,000; Full time

Job summary

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

Responsibilities

• 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?

Job description

Meta was built to help people connect and share, and over the last decade our tools have played a critical part in changing how people around the world communicate with one another. In the pursuit of personal superintelligence, Meta's AI systems are becoming more capable, and evaluating their safety is critical.

Meta is seeking Research Interns to join our Safety Evals and Red Teaming team within the Products and Applied Research org. We are seeking individuals passionate in areas such as Agent Safety, Benchmarks and Evaluations, Synthetic Data Generation, Automated Red teaming, LLM-as-a-Judge, benchmark design, eval harnesses, prompt injection, agent environments. Our internships are 16 weeks long and we have various start dates throughout the year.

What You Could Work On:

Depending on your interests and the team’s priorities, a project could address questions such as:

• How reliably do LLM-based judges identify safety-policy violations across different tasks, prompts, and adversarial conditions? How should we measure their errors and consistency?
• 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?