Anthology Fellow (Postdoctoral, 2-Year Term)

Anthology•Cambridge, MA

4d•$90,000 - $100,000•Hybrid

About The Position

Anthology is a Boston-based genome design company. We engineer fungi through advanced genetics, hardware design, and AI to manufacture functional proteins at 5–10× lower cost compared to traditional methods. Our goal is to build a resilient protein and biomolecule supply chain for human and planetary health. Backed by leading deep-tech VCs, we have partnered with global nutrition and ingredient manufacturers to bring cost-effective proteins to market. Everyone building AI for biology is competing for the same scarce resource, and it isn't compute or architecture — it's data linking genotype to phenotypes that matter industrially and commercially. Anthology generates that data itself in a closed loop. We diversify genomes at a scale rational design can't reach using modern genome engineering tools. We screen the variants on instruments we build in-house: droplet microfluidics that assay protein secretion and biomass simultaneously, spore-level FACS, high-efficiency transformation hardware, and continuous evolution devices that adapt strains to unconventional feedstocks. Sequencing winners and losers turns every campaign into datasets connecting genome architecture to measured manufacturing performance, something models trained on evolutionary data barely cover. Protein language models are already part of our design workflow; genome-scale models trained on our own data are the next step, and the Anthology Fellow will help build toward them. Working directly with the CTO, you will help set the research agenda rather than execute someone else's, and we expect you to publish.

Requirements

Ph.D. (completed, or expected within six months) in AI x Bio, bioinformatics, genomics, machine learning, synthetic biology, or a related field
Demonstrated research independence — a first-author publication, a clear sense of what you'd pursue here, and comfort with genuine ambiguity
Strong coding and end-to-end fluency with sequencing data: assembly, alignment, annotation, variant calling, and their failure modes
Hands-on experience training, fine-tuning, or applying genome language models or other genome-scale models, and the judgment to know how to choose and integrate them
Willingness to spend real time alongside the genetics and hardware teams; this isn't a laptop-only role
Able to work hybrid/on-site in Cambridge, MA
Authorized to work in the United States (STEM-OPT is welcomed)

Nice To Haves

Genomics experience in any eukaryotic system — fungal, animal, or plant. Filamentous fungi or yeast is a plus; picking up new systems fast matters more
Long-read sequencing and structural variant calling
Familiarity with mobile genetic elements and genome rearrangement techniques
Experience with high-throughput screening data from droplet microfluidics, FACS, or mass spectrometry
Grant writing experience (NSF, DOE, NIH, ARPA-E, ARPA-H, ARIA, or similar)

Responsibilities

Treat diversification as a design problem rather than a fixed protocol: what genomic diversity to generate, where, and in how many rounds
Analyze large variant libraries: structural variation, copy number, and regulatory change, mapped against phenotypes measured on our own instruments
Improve the genome annotation layer that downstream work depends on; annotation in non-model organisms is poor, and every error propagates
Adapt and evaluate genome-scale sequence models against our internal genotype–phenotype data, and turn their output into design decisions that close the loop
Partner with the genetics and hardware teams on what to measure and how, including device changes that would unlock data we can't currently collect
Support grant applications and academic collaborations, including joint proposals with partner labs at MIT, Harvard, and elsewhere
Publish and present externally, representing Anthology's science in the literature and at conferences