Search for Red Team Specialist roles in New York, focusing on AI security, with a salary range of $275,000 to $355,000, requiring a minimum of a Bachelor's degree, and looking for positions that offer visa sponsorship.

Okay, I've searched for Red Team Specialist roles in New York within AI security, targeting a salary range of $275,000 to$ 355,000, requiring a Bachelor's degree, and which offer visa sponsorship. I found 32 positions matching your criteria.

Red Team Specialist

New York, NY

AI/ML Security

$275000+

$355000-

Bachelor

Visa Sponsorship

Can you help me to analyze the job description and company culture?

Sure. Here's the analysis:

Job Analysis:

The Red Team Specialist role at Anthropic is fundamentally about ensuring the safety and security of their AI systems and products by proactively identifying and addressing potential vulnerabilities. This involves not only traditional security practices but also a deep understanding of the unique challenges posed by advanced AI capabilities. The primary responsibilities include conducting adversarial testing, developing comprehensive attack scenarios, and collaborating across technical teams to translate findings into actionable improvements. Success in this role hinges on a blend of technical acumen in web application security, creativity in attack simulation, and strong communication skills to convey complex concepts to diverse audiences. Candidates will likely face challenges related to the rapidly evolving nature of AI and its associated risks, calling for a mindset that embraces both innovation and mitigation strategies. Performance expectations will include developing systematic methodologies for testing, creating automated frameworks for continual assessment, and establishing metrics to gauge the effectiveness of detection systems—key indicators of the candidate's success within the first year.

Company Analysis:

Anthropic occupies a unique space in the AI research industry, focusing on creating reliable, interpretable, and steerable AI systems. As a public benefit corporation, it prioritizes the societal implications of AI technology, positioning itself as a responsible player amidst a landscape of rapid digital evolution. The company is characterized by a collaborative and research-driven culture, emphasizing the importance of communication and interdisciplinary teamwork. This role is part of the Safeguards team, which indicates a proactive approach to safety across the organization. Given the company’s mission, the Red Team Specialist role serves as a crucial component in scaling operations responsibly, aiming to fortify the integrity of AI systems against potential threats. Employees need to navigate the balance between innovation and safety carefully, thus the organizational culture fosters creativity while still demanding rigorous analytical thinking. The long-term potential for someone in this role includes significant influence over product design and efficacy, directly impacting the company's goal of delivering trustworthy AI solutions.

Mock up some interview questions based on the job description.

Absolutely. Here are some mock interview questions that could come up:

Describe a past experience where you uncovered a critical vulnerability in a system. What steps did you take to address it?
Tell me about a time you had to collaborate with multiple teams to achieve a project goal. How did you ensure effective communication?
Can you share an example of a creative attack simulation you designed? What was the outcome?
What would be your approach to developing a testing methodology for assessing AI systems specifically?
How do you stay updated on emerging vulnerabilities and trends in application security?
What testing tools have you found most effective in your red teaming efforts, and why?
Given an AI system's new feature release, describe how you would approach testing for vulnerabilities.
Imagine you are tasked with simulating an attack on a new product feature that utilizes advanced AI capabilities. What initial steps would you take?
If you were faced with resistance from product teams regarding your findings, how would you persuade them to take action?
Why are you interested in working at Anthropic, and how do you align with our mission of creating safe AI?
What excites you the most about the challenges of securing AI systems compared to traditional software frameworks?
What does success look like for you in a red teaming role within a company like Anthropic?
How do you think the principles of AI safety influence the development of security strategies?

Job Details

Overview Company

Red Team Specialist

$275k/y-$355k/y

Anthropic

a day ago

Highlight

HybridFull-timeMid

Summary

Anthropic is seeking a Red Team Specialist, Safeguards to join their team in New York, NY. The role involves ensuring the safety of deployed AI systems by uncovering vulnerabilities and simulating sophisticated threat actors.

About the Role

As a Red Team Specialist, Safeguards, you will conduct comprehensive adversarial testing across Anthropic’s product surfaces, develop creative attack scenarios, and research novel testing approaches. You will design and execute 'full kill chain' attacks, build systematic testing methodologies, and develop automated testing frameworks. Collaboration with Product, Engineering, and Policy teams to translate findings into improvements is essential.

About You

Required:

Demonstrated experience in penetration testing, red teaming, or application security.
Strong technical skills in web application security, including hands-on expertise with security testing tools (Burp Suite, Metasploit, custom scripting frameworks, etc.).
A track record of discovering novel attack vectors and chaining vulnerabilities in creative ways.
Experience with security testing tools and the ability to build custom automation.
Strong written and verbal communication skills, with the ability to explain technical concepts to varied audiences.
Proven ability to think like an attacker.

Preferred:

Experience with AI/ML security or adversarial machine learning.
Experience testing API security and rate limiting systems.
Background in testing business logic vulnerabilities and authorization bypass techniques.
Background in anti-fraud, trust & safety, or abuse prevention systems.
Familiarity with distributed systems and infrastructure security.
Understanding of AI safety considerations beyond traditional security.

Benefits

Competitive compensation with an annual salary range of $275k–$355k.
Optional equity donation matching.
Generous vacation and parental leave.
Flexible working hours.
Lovely office space in San Francisco.

Anthropic

We're an AI research company that builds reliable, interpretable, and steerable AI systems. Our first product is Claude, an AI assistant for tasks at any scale.

Our research interests span multiple areas including natural language, human feedback, scaling laws, reinforcement learning, code generation, and interpretability.

New York, NY