AI Studio Coach- LLM Red Teaming

Break Through Tech•New York, NY

2d•Remote

About The Position

Break Through Tech seeks subject matter experts to coach undergraduate fellows in a 16-week LLM Red Teaming program within its flagship extracurricular AI Program. Fellows will have completed a Machine Learning Foundations course and an industry-sponsored AI project. With guidance from Coaches, they will learn to ethically probe large language models for safety and security vulnerabilities using sanctioned platforms and jailbreaking techniques, document their findings, and participate in a red teaming competition. The curriculum covers Red Teaming Foundations, Direct Prompt Injection, Indirect Prompt Injection, and Live Competition Prep. Asynchronous coursework is supplemented by biweekly virtual events and peer activities. Coaches prepare and facilitate virtual events, develop supplementary slides and concept reviews based on course content, monitor fellow progress in Canvas, grade portfolio deliverables, host virtual office hours, and engage with fellows in Discord. They reinforce ethical red teaming throughout the program. Each Coach supports up to 50 fellows and may also engage with the wider cohort of up to 500 fellows in shared activities, including Workshops, Maker Days, and the program Discord. The role is part-time, remote, and temporary, beginning January 4, 2027 and ending May 20, 2027. The estimated commitment is an average of 15–20 hours per week, varying with program activities. Coaches complete about 10 hours of pre-program training in early January and must be available to facilitate eight events between January and May: four 90-minute Workshops and four 3-hour Maker Days. The role pays $35 per hour and is not eligible for benefits. It is open to eligible candidates across the United States; visa sponsorship is unavailable, though candidates authorized to work through F-1 CPT or OPT may apply.

Requirements

Demonstrated aptitude for LLM red teaming, assessed through an exercise provided by Break Through Tech and a relevant work sample such as a writeup, project, or portfolio piece.
Experience using large language models and advanced prompt engineering techniques.
Commitment to ethical, responsible red teaming and ability to model and uphold these practices with fellows.
Strong analytical and creative problem-solving skills.
Excellent written, verbal, and interpersonal communication skills.
Experience evaluating technical work and providing constructive feedback.
Strong organizational and time-management skills, including the ability to work independently in a remote environment.
Experience planning and facilitating live events, workshops, or group discussions; virtual experience and experience with undergraduate audiences are particularly relevant.
Commitment to developing inclusive and equitable working relationships with fellows from a variety of backgrounds.
Availability for about 10 hours of pre-program training in early January 2027 and to facilitate eight events on dates to be determined between January and May 2027.

Nice To Haves

Bachelor’s or Associate’s degree in computer science, cybersecurity, computational linguistics, or a related field, or equivalent practical experience.
Hands-on experience with ethical, sanctioned LLM red teaming challenges or competitions on platforms such as Gray Swan Arena, Lakera Agent Breaker, or HackAPrompt, including applying and iterating on common jailbreaking or prompt injection techniques.
Professional background in AI security, trust and safety, or ethical red teaming at a foundation AI lab, enterprise, or security firm.
Experience teaching, tutoring, serving as a teaching assistant, or mentoring undergraduate students or early-career professionals.

Responsibilities

Prepare and facilitate concept reviews and hands-on activities for four Workshops and four Maker Days, drawing on Canvas course materials and current developments in LLM red teaming, AI safety, and security.
Review scheduled red teaming challenges before events, confirm they remain active, test them, document how to complete them, and guide fellows through the experience.
Create and monitor breakout rooms, ensure compliance with program requirements and ethical standards, address fellow concerns, and provide feedback and suggestions.
Track event attendance and ensure fellows complete post-event surveys.
Review weekly SME-developed Canvas content to stay ahead of fellows’ learning and anticipate support needs.
Provide technical mentorship to fellows individually and in small-group office hours on LLMs, red teaming, and jailbreaking.
Monitor and respond to curriculum-related questions in Discord.
Reinforce ethical practices, responsible disclosure, and safety precautions throughout the program.
Provide written and oral feedback on fellows’ red teaming attempts, primarily through Gray Swan Arena.
Share timely resources in Discord, including papers, news, competitions, and notable jailbreak research.
Participate actively in weekly Community of Practice meetings with other Coaches and program staff to share ideas and troubleshoot.
Review Canvas assignments, score them using a grading rubric, and provide written feedback where applicable.
Review Canvas knowledge checks to identify areas of difficulty and use the findings to develop Workshop and Maker Day concept reviews and activities.
Work with program staff to identify fellows not meeting program expectations and assist with supportive interventions and follow-up.