- Project/Division: AI, Foundational Research
- Start date: As soon as possible
- Status: Full-time
- Work location: In-person, Bay Area
- Approximate compensation: $195,000 – $300,000, based on experience
- Reports to: Wet Lab Lead
THE ROLE
SecureBio is hiring a Senior Research Scientist to design and run the in vitro capability-verification experiments that our Foundational Research team will use to establish how in silico model performance holds up in real biology.
Our in silico evaluations have become de facto standards, and frontier labs run them before releasing models to the public. Our work has been cited in model cards from OpenAI, Anthropic, and Google, and has informed safeguards on frontier models. We are a member of the NIST US AI Safety Consortium and a partner to the European AI Office.
It remains an open question whether such digital proxies can truly serve to underpin pivotal, consequential decisions regarding biological risks in AI. That is the question that you will seek to answer.
THE TEAM
Our Foundational Research team builds the measurement tools for capabilities that do not yet have established methods. The capability verification workstream complements our work in uplift and hybrid evaluation development.
This kind of work is new: AI just may accelerate biotechnology like semiconductors did computing half a century ago. We think this demands a research facility with the creativity, flexibility, and resources to keep pace; a sort of Bell Labs for biosecurity. We are looking for someone with strong research taste who can work with a diverse team to design rigorous studies from scratch and rapidly produce results that are clear and convincing to AI firms, researchers, and policymakers.
We are currently building a BSL-2 lab and expanding the team that will work from it. You would join early enough to have a significant opportunity to shape both of these.
RESPONSIBILITIES
- Design and run in vitro validations of specific capabilities that LLMs and biological AI models demonstrate computationally, on turnarounds short enough to inform pre-release decisions.
- Own experimental design rigor across verification studies: power, controls, bias mitigation, replicability, and confound management.
- Translate candidate verification tasks into executable experiments, including choosing proxy systems that are both informative about the capability of concern and safe to run.
- Critically assess results, and put them in the context of the major threat models.
- Work with the evals team to turn verification findings into in silico correlates, so that expensive wet-lab evidence becomes a cheap and repeatable measurement.
- Oversee wet lab technical team in the implementation and execution of studies.
- Contribute to specification and biological task design for studies of AI uplift of human performance of biology research.
- Design and execute demonstrations for policymakers and frontier labs, where the result has to be both rigorous and legible to a non-specialist audience.
- Contribute to reports, papers, and our public dashboard https://securebio.org/benchmarks/ of trends in AI biology capabilities.
QUALIFICATIONS AND SKILLS
A strong candidate would have the following qualifications:
- A PhD in virology, molecular biology, synthetic biology, protein design, or a closely related field, plus several years of post-PhD experience. We will consider equivalent depth from other paths, but we expect most strong applicants to hold a doctorate.
- Hands-on wet-lab depth in at least one relevant area, with the ability to interface across the others.
- Past experience working with ≥ BSL-2 agents.
- Strong experimental design skills: power analysis, controls, and confound management, applied to small-n studies.
- Calibrated judgment about biological risk.
- Comfort with novel, non-standardized work where you define the method, and with short, intensive project cycles that shift with model releases.
- Commitment to research ethics,…