Job Description

About the Team
The team is missioned to build infrastructures, platforms and technologies, as well as to support cross-functional teams to protect our users, products and infrastructures. In this team, you'll have a unique opportunity to have first-hand exposure to the strategy of the company in key security initiatives, especially in building scalable and secure-by-design systems and solutions. Our challenges are not your regular day-to-day technical problems; you'll be part of a team that's developing new solutions to new challenges of a kind not previously addressed by big tech. It's working fast, at scale, and we're making a difference.

As a project intern, you will have the opportunity to engage in impactful short-term projects that provide you with a glimpse of professional real-world experience. You will gain practical skills through on-the-job learning in a fast-paced work environment and develop a deeper understanding of your career interests.

Applications will be reviewed on a rolling basis - we encourage you to apply early.

Successful candidates must be able to commit to at least 3 months long internship period.

Responsibilities:
- Platform Engineering (Full Stack): Develop the RedCheck platform (Go/React), focusing on features like automated task scheduling, visualized risk reporting, and end-to-end evaluation workflows.
- Model & Agent Integration: Build robust adapters to connect RedCheck with a wide variety of targets—including OpenAI-compatible models, internal RPC agents, and multi-modal systems (Text/Image/Video)—ensuring stable, high-throughput interactions.
- Automated Evaluation Pipelines: Implement engineering pipelines for "AI Red Teaming". This involves automating the injection of attack prompts and using "Judge Models" to evaluate the safety of the target's response.
- Reliability & Optimization: Optimize the system to handle large-scale datasets (e.g., 7000+ test cases) and ensure reliable execution of long-running evaluation tasks.