We’re building a team that will research and mitigate extreme risks from future models.

This team will intensively red-team models to test the most significant risks they might be capable of in areas such as biosecurity, cybersecurity risks, or autonomy. We believe that clear demonstrations can significantly advance technical research and mitigations, as well as identify effective policy interventions to promote and incentivize safety.

As part of this team, you will lead research to baseline current models and test whether future frontier capabilities could cause significant harm. Day-to-day, you may decide you need to finetune a model to see whether it becomes superhuman in an eval you’ve designed; whiteboard a threat model with a national security expert; test a new training procedure or how a model uses a tool; or brief government, labs, and other research teams. Our goal is to see the frontier before we get there.

We’re currently hiring for our CBRN workstream, with an emphasis on biosecurity risks. By nature, this team will be an unusual combination of backgrounds. We are particularly looking for people with experience in these domains:

• Biosecurity: You're a biologist who's concerned about the implications of AI development. You're an academic who researches biosecurity defense. You have experience modeling biological phenomena or developing advanced threat modeling simulations. 
• Science: You’re an ML researcher who builds agents to augment chemistry or biology research. You’ve built a protein language model and you enjoyed looking through the embedding space. You’re a team lead at an ML-for-drug discovery company. You’ve built software for astronauts or materials scientists.
• Evaluations: You’ve managed a large-scale benchmark development project, in AI or other domains. You have ideas about how AI and ML evaluations can be better.

Do not rule yourself out if you do not fit one of those categories - it’s plausible the people we’re looking for do not fit any of the above! If you think about the most significant upsides and downsides of AI, and you can do good research to get glimpses of what those look like, please consider applying.

Please note: We will only be considering candidates who can be based in the Bay Area for this role.

Responsibilities

• Independently lead small research projects while collaborating with team members on larger initiatives
• Design, run, and analyze scientific experiments to advance our understanding of large language models
• Work with external partners to develop novel evaluations to accurately assess the biosecurity implications of our models
• Synthesize biosecurity research to establish thresholds of concern for AI capabilities
• Develop a framework for how we might assess the impact of AI on biosecurity
• Communicate our findings to external stakeholders, such as policymakers

You may be a good fit if you

• Have one of:
• Advanced degree (MS or PhD) in the biological sciences (Molecular Biology, Computational Biology, Bioengineering) or 4+ years of professional experience in biology research (including wet-lab) and some familiarity with machine learning or software engineering (Python preferred)
• Professional work experience in software engineering or machine learning and professional work experience in biosecurity
• Have expertise in Python and experience with deep learning frameworks (PyTorch preferred)
• Have familiarity with prompting and engineering large language models
• Have previous experience leading large projects with multiple external collaborators or stakeholders
• Are able to balance research goals with practical engineering constraints
• Have strong problem-solving skills and a results-oriented mindset
• Have excellent communication skills and ability to work in a collaborative environment
• Pick up slack, even if it goes outside your job description
• Prefer fast-moving collaborative projects to extensive solo efforts
• Care about the societal impacts of AI

Strong candidates may also have experience with

• Wet lab experience in molecular biology
• Previous experience with developing evaluations or benchmarks for large language models
• Familiarity with GPUs, Kubernetes, and OS internals
• Experience with language modeling using transformer architectures
• Previous experience in emerging technology policy, including in biosecurity or AI

Representative projects

• Design and implement a new evaluation to test models for CBRN risks
• Manage a large-scale automated evaluations run across our clusters
• Develop a detailed threat model of CBRN risks, and identify how core bottlenecks can be resolved from further evaluations
• Prepare briefing materials to share the results of an evaluation run with external research groups

Candidates need not have

• Previous professional experience in AI Safety
• 100% of the skills needed to perform the job

Deadline to apply: None. Applications will be reviewed on a rolling basis.