Offensive Security Research Engineer, Safeguards

About Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

About the Role

We are looking for vulnerability researchers to help mitigate the risks that come with building AI systems. One of these risks is the potential for LLMs to enable adversaries to cause harm by automating the attacks that today are carried out by human cybercrime groups, but in the future may be easily carried out by humans misusing LLMs. We are hiring security specialists who are experienced at exploitation and remediation, and are interested in understanding how LLMs could cause harm in the future, so that we can better prepare for this future and mitigate these risks before they arise.

Responsibilities:

• Triage any vulnerabilities discovered, coordinate and assist the external and open-source community in remediation
• Write scaffolds designed to automate typical traditional attack techniques to help clarify our defensive problem selection
• Research how adversaries might mise-use LLMs to identify and exploit vulnerabilities at scale in the future
• Develop promising defensive strategies that could mitigate the ability of adversaries to mis-use models in harmful ways
• Work with a small, senior team of engineers and researchers to enact a forward-looking security plan

You may be a good fit if you have:

• 3+ years experience with pentesting, vulnerability research, or other offensive security experience
• Senior-level knowledge in at least one related topic area (reverse engineering, network security, exploitation, physical security)
• A history demonstrating desire to do the “dirty work” that results in high-quality outputs
• Software engineering experience
• Demonstrated success in bringing clarity and ownership to ambiguous technical problems
• Proven ability to lead cross-functional security initiatives and navigate complex organizational dynamics

Strong candidates may also have:

• Published research papers on computer security, language modeling, or related topics; or given talks at Defcon, Blackhat, CCC, or related venues
• Familiarity with large language models and how they work; for example, you may have written agent scaffolds
• Reported CVEs, or been awarded for bug bounty vulnerabilities
• Contributed to open-source projects in LLM- or security-adjacent repositories

The annual compensation range for this role is listed below.

For sales roles, the range provided is the role’s On Target Earnings ("OTE") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.

Annual Salary:

$320,000—$405,000 USD

Logistics

Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience.

Location-based hybrid policy:** Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices.

Visa sponsorship: We do sponsor visas! However, we aren't able to successfully sponsor visas for every role and every candidate. But if we make you an offer, we will make every reasonable effort to get you a visa, and we retain an immigration lawyer to help with this.

We encourage you to apply even if you do not believe you meet every single qualification. Not all strong candidates will meet every single qualification as listed. Research shows that people who identify as being from underrepresented groups are more prone to experiencing imposter syndrome and doubting the strength of their candidacy, so we urge you not to exclude yourself prematurely and to submit an application if you're interested in this work. We think AI systems like the ones we're building have enormous social and ethical implications. We think this makes representation even more important, and we strive to include a range of diverse perspectives on our team.

Your safety matters to us. To protect yourself from potential scams, remember that Anthropic recruiters only contact you from @anthropic.com email addresses. In some cases, we may partner with vetted recruiting agencies who will identify themselves as working on behalf of Anthropic. Be cautious of emails from other domains. Legitimate Anthropic recruiters will never ask for money, fees, or banking information before your first day. If you're ever unsure about a communication, don't click any links—visit anthropic.com/careers directly for confirmed position openings.

How we're different

We believe that the highest-impact AI research will be big science. At Anthropic we work as a single cohesive team on just a few large-scale research efforts. And we value impact — advancing our long-term goals of steerable, trustworthy AI — rather than work on smaller and more specific puzzles. We view AI research as an empirical science, which has as much in common with physics and biology as with traditional efforts in computer science. We're an extremely collaborative group, and we host frequent research discussions to ensure that we are pursuing the highest-impact work at any given time. As such, we greatly value communication skills.

The easiest way to understand our research directions is to read our recent research. This research continues many of the directions our team worked on prior to Anthropic, including: GPT-3, Circuit-Based Interpretability, Multimodal Neurons, Scaling Laws, AI & Compute, Concrete Problems in AI Safety, and Learning from Human Preferences.

Come work with us!

Anthropic is a public benefit corporation headquartered in San Francisco. We offer competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a lovely office space in which to collaborate with colleagues. Guidance on Candidates' AI Usage: Learn about our policy for using AI in our application process