Senior Scientist, AI-Assisted Lab Optimization

Division: Detection, in close partnership with SecureBio AI Start date: as soon as possible Starting compensation: $180,000 to $210,000, depending on experience Work location: In-person in Cambridge, MA About SecureBio SecureBio is a 501(c)(3) non-profit dedicated to protecting civilization from catastrophic biological risks, particularly pathogens designed to evade detection. We operate two divisions, SecureBio Detection and SecureBio AI, and serve as a technical advisor to the US and allied governments. Our Detection team co-leads the world’s largest wastewater metagenomic sequencing network, monitoring more than 20 million people across 30 or more sewersheds and generating over half of all public untargeted wastewater sequencing data worldwide. We have twice flagged aberrant engineered sequences in the wild and traced them to their sources. Our AI team builds industry-standard evaluations of frontier models’ biological capabilities, including the Virology Capabilities Test and the agentic ABC-Bench, now cited in the model cards and risk frameworks of every major AI lab and referenced in US Congressional hearings. The two divisions operate differently. Detection is in person, lab based and growing quickly. AI is fully remote, distributed from Berkeley to Berlin to Melbourne. This is the first role to sit formally across both, and the first time the two teams have worked toward a shared goal, which is a significant part of why we are hiring at this level. The opportunity Metagenomic surveillance is the most robust defense we have against novel or engineered biological threats, but its value depends on speed and sensitivity. Against a pathogen with a three day doubling time, shaving even eleven days off the path to a confident answer lets authorities intercept an outbreak while it is roughly thirteen times smaller. The downstream impact of speed is, quite literally, exponential. At the same time, the rapid development of general AI capabilities has raised serious concerns that bad actors could use these tools to cause harm through biology. Large language models already exceed human experts on lab oriented practical knowledge evaluations such as our own Virology Capabilities Test ( VCT). Whether that translates into meaningful uplift in a working laboratory remains unresolved, and it is one of the more consequential open questions in biosecurity today. We are launching a proof of concept program to answer it, using our detection pipeline as the case study, and we are hiring a senior wet lab scientist to lead it. You will be embedded in an AI driven R&D loop, using frontier models as collaborative partners to optimize the wet lab protocols underpinning SecureBio Detection, while generating the data and intuition that guide SecureBio AI’s research into biosecurity relevant uplift. Two things come out of this work. A detection pipeline that is measurably better than it was. And a rigorous, honest account of what AI uplift looks like for an expert biologist doing real work, including where the models mislead as well as where they help, which is the part the field is currently missing. You will have a great deal of independence, and discretion to devote significant resources toward the success of the project. You will also serve as a key link between the two major groups within SecureBio, which is why we place unusual weight on communication and creativity in the requirements below. At its heart, this is an opportunity to apply cutting edge tools to an important problem, and to see the results of your creativity and dedication produce tangible, measurable benefits to biosafety. What you’ll do You will lead a hands-on, AI-in-the-loop wet lab R&D program, owning it from experimental design through execution, analysis and documentation. Concretely, you will: Work with the Detection team to identify opportunities for structured optimization experiments on viral enrichment, host and background depletion, nucleic acid extraction, and sequencing library preparation. Partner with frontier AI models as collaborative design partners, prompting them to propose and prioritize high impact protocol modifications from the molecular literature, to help structure experimental designs, and to interpret QC and sequencing output and recommend the next iteration. How that partnership is best structured is itself an open question. Whether you work with one model continuously, run several in parallel and cross assess their outputs, or develop an approach we have not yet considered, is something we hope this program will teach us. Execute these experiments at the bench, working toward a set of ambitious improvement targets. Some of this you will do yourself. Some you will coordinate across the detection scientists and research associates, with the full support of the laboratory and the lab automation work that follows it. Build QC feedback loops that aggregate historical sequencing reports and protocol metadata, so that models can suggest improvements grounded in our own data rather than the literature alone. Benchmark results rigorously, establishing reproducible metrics and controls so that improvements are real and demonstrably AI attributable. Establish how this work is captured. We do not yet have a logging system, and we want a codified approach to labelling and annotating these interactions so that we can later interrogate the record and identify where the models genuinely contributed. You would design that with us. Produce a qualitative, well documented case study of how, and how much, frontier AI uplifts an expert biologist in a complex wet lab setting, directly informing AI safety and CBRN threat modeling. Maintain documentation in electronic lab notebooks and uphold rigorous QA/QC throughout. In this role the record is not administrative overhead, it is one of the primary deliverables. Alongside the core program, you will help colleagues across the laboratory apply these tools more effectively in their own work. You will work in close partnership with SecureBio’s AI, computational and laboratory science leadership, who will provide scientific direction and computational support. Required qualifications PhD in molecular biology, microbiology, bioengineering or a related field, or an MS with an equivalent depth of hands-on experience. Deep, hands-on wet lab expertise in relevant protocols, including viral enrichment, nucleic acid extraction and NGS library preparation, with protocol development as a substantive focus of your work rather than an occasional part of it. A demonstrated track record of optimizing and troubleshooting complex molecular protocols, supported by rigorous experimental design and quantitative data analysis skills. Strong, current and self directed fluency with frontier AI tools in your own scientific work. We are looking for an iterative working relationship with these models, in which you interrogate and push back on outputs, recognize when a suggestion is plausible but experimentally unsound, and treat the model as an instrument you are actively calibrating. Excellent communication and collaboration habits. This role sits between two teams with different cultures and different working rhythms, and the ability to operate credibly in both is central to its success. It carries more weight here than it would in most laboratory roles. A proven ability to own a research program independently, exercising sound scientific judgment with limited supervision. There is no established template for this position and no internal precedent for it, so you will be defining much of your own scope early on, with our full support. Preferred qualifications Experience with metagenomic sequencing and environmental samples such as wastewater. Depth here is valuable, though a good deal of it can be learned alongside the Detection team. Experience with technically demanding sample types more broadly, including soil, leaf litter, marine and sediment work. Wastewater is a complex, variable and inhibitor rich matrix, and scientists who have worked in that space tend to recognize quickly where the most meaningful gains are available. Experience working with RNA. Much of the environmental metagenomics community works predominantly with DNA, and familiarity with the additional demands of RNA is a strong advantage here. A background in molecular ecology or environmental microbiology, and a varied research history more generally. This work rewards breadth and creativity across problem types. Familiarity with liquid handling automation such as Opentrons, Hamilton or Tecan. We have an existing automation foundation and plan to expand it, and we expect the person in this role to influence that direction. Working knowledge of bioinformatics and sequencing QC pipelines, and scripting in Python or R for data analysis. Prior work in biosecurity, pandemic preparedness or a related mission driven setting. Background in viral ecology, low abundance or rare target detection, targeted sequencing, probe capture enrichment or host depletion chemistries. Logistics and benefits This is a full-time in-person role located in our Cambridge, MA office. Our employee benefits reflect our belief in investing to build the strongest possible team, in which everyone receives the trust and support they need to excel. Our benefits package includes: Flexible work hours; unlimited paid time off (PTO) for all employees; and minimum 12 weeks fully-paid parental leave. 401(k) Employer 401(k) match up to 4% of total salary. Excellent offices Superb working environments in our Kendall Square offices, including high-quality ergonomic office equipment, snacks, and daily catered lunches. Referral bonus We offer a referral bonus of up to $4,000 to individuals who refer successful candidates for this position: If you refer a candidate that we invite to an in-person work trial, you will receive $800; If the candidate accepts a job offer, you will receive a further $3,200, for a total of $4,000. To receive these bonuses, we must reasonably believe that you were responsible for referring the candidate to us. #J-18808-Ljbffr SecureBio, LLC