Berkeley, California or Hybrid
METR’s current priority is to develop evaluations for AI R&D capabilities. We want to provide an early warning before AI agents might dramatically improve themselves and kick off an ‘explosion’ of dangerous capabilities.
METR is hiring ML research engineers/scientists to drive the development of these AI R&D evaluations forward. (More here.)
Responsibilities:
- Design tasks/benchmarks that can determine if a model is dangerous.
- Run evaluations on current models, sometimes in collaboration with partners in governments or frontier AI companies.
- Rapidly execute experiments to determine how different elicitation techniques affect results.
- Think carefully about principled approaches to measuring AI capabilities, and run experiments to evaluate them.
In addition to creating AI R&D evals, METR is interested in developing the “science of evals” and standards for alignment. Our technical team is currently small (~17 people), so you will have an opportunity to shape our future direction.
What we’re looking for
An ideal candidate would be a machine learning researcher with substantial experience working on frontier LLMs and a track record of successful execution-heavy research projects. Specifically, we're looking for people who have:
- A strong ML publication record (e.g. have published several first-author papers at leading ML conferences),
- Experience working directly on a scaling / pretraining team at frontier LLM labs, or
- Multiple years of experience solving challenging ML engineering or research problems at frontier LLM labs.
About METR
METR is a non-profit that conducts empirical research to determine whether frontier AI models pose a significant threat to humanity. It is robustly good for civilization to have a clear understanding of what types of danger AI systems pose, and know how high the risk is. You can learn more about our goals from our published talks (overall goals, recent update).
Some highlights of our work so far:
- Establishing autonomous replication evals: Thanks to our work, it’s now taken for granted that autonomous replication (the ability for a model to independently copy itself to different servers, obtain more GPUs, etc) should be tested for. For example, labs pledged to evaluate for this capability as part of the White House commitments.
- Pre-release evaluations: We’ve worked with OpenAI and Anthropic to evaluate their models pre-release, and our research has been widely cited by policymakers, AI labs, and within government.
- Inspiring lab evaluation efforts: Multiple leading AI companies are building their own internal evaluation teams, inspired by our work.
- Early commitments from labs: Anthropic credited us for their recent Responsible Scaling Policy (RSP), and OpenAI recently committed to releasing a Risk-Informed Development Policy (RDP). These fit under the category of “evals-based governance”, wherein AI labs can commit to things like, “If we hit capability threshold X, we won’t train a larger model until we’ve hit safety threshold Y”.
We have been mentioned by the UK government, Time Magazine, and others. We’re sufficiently connected to relevant parties (labs, governments, and academia) that any good work we do or insights we uncover can quickly be leveraged.
Logistics
Deadline to apply: None. Applications will be reviewed on a rolling basis.
Compensation: $276,000—$420,000 USD salary range plus employee benefits
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.
Having said that, if you’re not able to start within four months of applying (e.g. because you’re getting a degree), it’s probably best if you wait to apply until you’re within four months of your intended start date. It's difficult for us to make offers with start dates more than four months in the future.
Apply for this job
We encourage you to apply even if your background may not seem like the perfect fit! We would rather review a larger pool of applications than risk missing out on a promising candidate for the position. If you lack US work authorization and would like to work in-person (preferred), we can likely sponsor a cap-exempt H-1B visa for this role.
We are committed to diversity and equal opportunity in all aspects of our hiring process. We do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. We welcome and encourage all qualified candidates to apply for our open positions.
Registering interest is quick; our main question can be answered with a few bullet points. Register interest!