Founding Scientist (Synthetic Genomics)

What if you could train a biological foundation model on... the entire internet? Exonic is pioneering a new generation of biological foundation models, focused on heterogeneous, unstructured, and noisy datasets. Our first application is the design of safer, more controllable, and more affordable gene therapies.

Exonic Biosciences · Dogpatch, San Francisco

$120K–$180K a year + equity

Exonic is building AI systems for programmable biology.

We train multimodal foundation models on large-scale biological datasets to design synthetic non-coding DNA. We experimentally validate our AI-designed systems in mammalian cells, with current applications in cell-type targeting and viral vector biomanufacturing.

Our core focus is synthetic regulatory DNA. We have already generated strong in vitro cell-type targeting results and are expanding our internal experimental platform in San Francisco.

We are looking for an ambitious experimental scientist to take ownership of Exonic’s wet-lab work and help push the platform into new directions.

You would work directly with the founder as one of the first people in the company.

What you’ll work on

• Own and execute experimental validation of AI-designed regulatory DNA
• Design and run cell-based assays for synthetic enhancer and expression systems
• Help advance programs in cell-type targeting and AAV manufacturing
• Help shape Exonic’s experimental roadmap as the company grows

Relevant experience

• Molecular biology, synthetic biology, regulatory genomics, or gene therapy
• Mammalian cell culture and cell-based assays
• Cloning, plasmid design, transfection, qPCR/ddPCR, sequencing, flow, luciferase, or related workflows
• AAV biology/manufacturing experience is a major plus

We care most about ownership, execution speed, and comfort with ambiguity.

This is an early-stage role with autonomy, and the opportunity to build the biological engine of an AI-native synthetic DNA company.

Location: San Francisco / MBC BioLabs

We train multimodal biological foundation models on large-scale heterogeneous biological datasets to design synthetic non-coding DNA. We experimentally validate our AI-designed systems in mammalian cells, with current applications in cell-type targeting and viral vector biomanufacturing.