Latest AI JobsBrowse Jobs
Anthropic logo

Red Team Engineer, Safeguards

AnthropicRemote-Friendly (Travel Required) | San Francisco, CASafeguards (Trust & Safety)
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Posted
10 Jul 2026
Status
Open · checked 7d ago

About this role

The Red Team Engineer, Safeguards position at Anthropic is an exciting opportunity for security professionals to take an adversarial approach to uncovering vulnerabilities across AI products and infrastructure. Based remotely or in San Francisco, CA, this role suits experienced security experts passionate about AI safety, trust, and safety.

Role Overview

Anthropic's Safeguards team seeks a Red Team Engineer to ensure the safety of deployed artificial intelligence systems and products. The professional in this role adopts an adversarial approach to discover vulnerabilities across the product ecosystem before malicious actors can exploit them. Responsibilities span from evaluating technical infrastructure on products to uncovering emergent risks tied to advanced AI capabilities. Professionals investigate various potential abuses, ranging from coordinated account manipulation and payment fraud to novel product feature exploitation, simulating sophisticated threat actors who chain multiple attack vectors together.

Key Responsibilities

Conduct comprehensive adversarial testing across product surfaces by building creative attack scenarios that merge multiple exploitation techniques.
Research and implement innovative testing approaches for emerging capabilities, including tool use, agent systems, and new interaction paradigms.
Design and execute full kill chain attacks emulating real-world threat actors attempting specific malicious objectives.
Build and maintain systematic testing methodologies that evaluate every system aspect.
Develop automated testing frameworks to facilitate continuous assessment at scale.
Collaborate closely with Engineering, Product, and Policy teams to translate testing findings into concrete system improvements.
Establish metrics to measure detection effectiveness against novel abuse.

Requirements

Experience in penetration testing, application security, or red teaming.
Experience executing model jailbreaking and testing large-scale agentic workflows for non-obvious prompt injection vectors.
Strong technical skills in web application security, alongside hands-on expertise with security testing tools such as Metasploit, Burp Suite, or custom scripting frameworks.
Experience building custom automation, including LLM-specific testing frameworks.
A documented track record of discovering novel attack vectors and chaining vulnerabilities creatively.
A public body of work, which may include CVEs, disclosed bug bounty reports, or blog posts.
Strong verbal and written communication skills to articulate technical concepts to varied audiences.
Bachelor’s degree or an equivalent combination of education, training, and experience in a relevant field of study.
Ability to meet location-based hybrid policies requiring staff to be in an office at least 25% of the time.

Nice to Have

Experience working with AI or machine learning security and adversarial machine learning.
Understanding of AI safety considerations extending beyond traditional security, including modern guardrails against jailbreaks.
Experience testing API security and rate-limiting systems.
Background in testing business logic vulnerabilities and authorization bypass techniques.
Background working in trust and safety, anti-fraud, or abuse prevention systems.
Familiarity with distributed systems, infrastructure security, and abuse detection mechanisms with the ability to engineer novel bypasses.
Adaptability to understand and build engagements addressing emerging threats outside a direct area of expertise.

Skills and Tools

LLM
Web application security
Burp Suite
Metasploit
Custom scripting frameworks
Automated testing frameworks

Salary and Benefits

The annual salary range for this position is $320,000 to $405,000 USD. Anthropic offers competitive compensation and benefits, optional equity donation matching, generous parental leave, flexible working hours, generous vacation, and collaborative office spaces. Visa sponsorship is available for qualifying candidates, supported by an immigration lawyer.

About the Company

Anthropic is a public benefit corporation headquartered in San Francisco with a mission to build reliable, interpretable, and steerable AI systems that remain safe and beneficial for society. The organization functions as a single cohesive team tackling large-scale research efforts as an empirical science, valuing collaboration, diverse perspectives, and long-term impact in artificial intelligence.

How to Apply

To apply for this position, please visit the official Anthropic careers page to submit an application.

Skills and tech stack

LLM

Questions candidates ask

What is the salary range for the Red Team Engineer role?

The annual salary range for this position is $320,000 to $405,000 USD.

Is this position remote or on-site?

This role is remote-friendly with travel required, and features a location-based hybrid policy where staff are expected to be in a company office at least 25% of the time.

Does Anthropic offer visa sponsorship for this role?

Yes, Anthropic sponsors visas for this role and retains an immigration lawyer to assist candidates who receive an offer, though sponsorship cannot be guaranteed for every applicant.

What qualifications are required regarding education?

Candidates need a Bachelor’s degree or an equivalent combination of education, training, and/or experience in a relevant field of study.

What core skills are expected from applicants?

Applicants should have experience in penetration testing, red teaming, or application security, model jailbreaking, web application security, custom automation building, and a public body of work like CVEs or bug bounty reports.

Ready to apply?

The application is on the official Anthropic careers page.

Apply on company site