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're building a team to develop and run "gold standard" evaluations for catastrophic risks, to make sure we release models that are safe for the world to use.This work is at the core of implementing our Responsible Scaling Policy (RSP), which defines the technical and operational measures for safely training and deploying frontier AI models.
As a Research Engineer on the Frontier Red Team, you'll be creating evaluation systems that will help us understand and control some of the most capable AI systems ever built. You will collaborate with domain experts across multiple workstreams including biosecurity, autonomous replication, cybersecurity, and national security. You'll build, scale, and run evaluations to measure dangerous capabilities in models and determine if and when they cross ASL thresholds and require heightened security measures. Your work will directly inform decisions at the highest levels of the company and help establish standards that could influence the entire AI industry.
We are looking for engineers who can execute rapidly, maintain high throughput, and bring a strong builder mindset to solving complex problems. The ideal candidate will be able to quickly prototype and iterate on evaluation infrastructure while maintaining high engineering standards. You'll be building systems to evaluate capabilities that have never existed before, requiring creative solutions and rigorous implementation.
Responsibilities
- Design and implement robust evaluation infrastructure to measure model capabilities and risks across multiple domains
- Lead technical projects to build and scale evaluation systems that could become industry standards
- Collaborate with domain experts to translate their insights into concrete evaluation frameworks
- Build sandboxed testing environments and automated pipelines for continuous model assessment
- Work closely with researchers to rapidly prototype and iterate on new evaluation approaches
- Partner with cross-functional teams to advance Anthropic's safety mission
- Contribute to Capability Reports that inform critical deployment decisions
You may be a good fit if you
- Have led and conducted fast, iterative experiments with frontier AI models
- Have designed or implemented evaluations that involve sampling + prompting LLMs
- Write clean, well-structured code that others can build upon
- Care deeply about AI safety and responsible development
- Have strong software engineering skills with extensive Python experience
- Have experience working with distributed systems
- Are comfortable defining technical specifications and executing towards them
- Are a self-starter who thrives in fast-paced, collaborative environments
- Are excited about tackling unprecedented technical challenges
- Can balance the urgency of our mission with careful, methodical implementation
Strong candidates may also have
- Experience working on sensitive or security-critical projects
- Understanding of AI safety concepts and concerns
- Background in one or more relevant domains (biosecurity, cybersecurity, and others)
Representative Projects
- Build infrastructure for running large-scale model evaluations across multiple risk domains
- Create tools for rapid evaluation prototyping and iteration
- Contribute to evaluation frameworks that could become industry standards
- Design and implement custom testing environments for specific capability assessments
- Develop monitoring and analysis systems for evaluation results
- Collaborate with domain experts to translate theoretical risks into practical tests, such as cyber ranges and autonomous replication environments
Candidates need not have
- Domain expertise in specific risk areas
- 100% of the skills needed to perform the job
- Prior experience with AI model evaluation
Deadline to apply: None. Applications will be reviewed on a rolling basis.
The expected salary range for this position is:
Annual Salary:
$280,000—$425,000 USD
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.
Top Skills
What We Do
Anthropic is an AI safety and research company that’s working to build reliable, interpretable, and steerable AI systems. Our research interests span multiple areas including natural language, human feedback, scaling laws, reinforcement learning, code generation, and interpretability.
.png)
