Software Engineer, Safeguards Research

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 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

The Safeguards Research Team conducts critical safety research and engineering to ensure AI systems can be deployed safely. As a Software Engineer on our team, you'll develop robust end-to-end pipelines and tooling that directly supports our safety research initiatives. You'll work on building scalable infrastructure for evaluating model behaviors, automating safety assessments, and implementing efficient data processing systems to help us understand and mitigate risks in advanced AI systems.

You take a pragmatic approach to software development, preferring simple, effective solutions over complex ones. You're adept at working with language models through effective prompting techniques and can translate research concepts into production-quality code. You'll collaborate closely with researchers to build tools that address both immediate safety challenges and support longer-term research initiatives.

Deep machine learning knowledge is not required for this role. The main requirement is a desire to understand researcher workflows and improve research productivity.

Representative projects:

• Design and implement end-to-end pipelines for efficient evaluation of model safety features and vulnerabilities


• Develop tooling to automate the generation and analysis of jailbreak attempts


• Build data processing systems that can handle large-scale model outputs


• Optimize Python code for memory efficiency and parallelization to improve research workflow performance


• Create flexible interfaces for researchers to interact with models and experimental setups


• Implement monitoring systems to track model behavior across different safety dimensions

You may be a good fit if you:

• Have strong software engineering experience, particularly with Python


• Are excited about learning foundational ML knowledge to make researchers more effective (deep ML knowledge is not required)


• Are experienced with prompting and working with language models


• Excel at building practical, scalable data pipelines and tooling


• Prefer implementing simple solutions that work reliably over complex ones


• Have experience optimizing code for performance and resource efficiency


• Are comfortable working in a fast-paced, collaborative research environment


• Care deeply about the impacts of AI

Strong candidates may also:

• Have experience building systems that integrate with large language models


• Have worked on distributed computing systems or parallel processing


• Have implemented data processing pipelines at scale


• Have contributed to open-source machine learning or AI safety tools


• Have experience with cloud infrastructure and containerization

The expected salary range for this position is:

Annual Salary: $300,000 - $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.

Note: Currently, the team has a preference for candidates who are able to be based in the Bay Area. However, we remain open to any candidate who can travel 25% to the Bay Area.

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.

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.

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.

The expected salary range for this position is:

Annual Salary:

$300,000—$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.

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.