David Kelley

Using computers to understand the molecular logic of life.

[David Kelley @drklly]

We’re hiring in my group at Calico. We build Borzoi and its successors—deep learning models that predict how every nucleotide shapes cell-type-specific gene regulation—and apply them to interpret human genetic variation.

[David Kelley @drklly]

@anshulkundaje @pkoo562 Wow, what a surprise to open X to such a kind and generous message! Incredible role models like yourself Anshul have been a major influence.

[David Kelley @drklly]

Apply or share if you know someone it'd suit: https://t.co/bwIWtJrnc3
In your cover letter, I'd encourage you to address why you want to work with us in particular, what problems you'd tackle, and what approaches you'd bring. Looking forward to meeting many great researchers!

[David Kelley @drklly]

We’re hiring in my group at Calico. We build Borzoi and its successors—deep learning models that predict how every nucleotide shapes cell-type-specific gene regulation—and apply them to interpret human genetic variation.

[David Kelley @drklly]

I’m looking for someone highly quantitative, deeply curious, and interested in how genomics research evolves as AI becomes a routine collaborator. You'd be joining a small, focused group with real ownership of your research direction.

[David Kelley @drklly]

Check out this exciting work from the Calico ML team, developing creative techniques to detect subtle information in rich measurements like MRI and analyze the genetic associations driving differences.

[Siva @scelesticsiva]

Genomics has scaled massively, but phenotyping is still painstakingly manual. What if we stopped throwing away the rich, subtle signals in medical images? We propose Vector2Variant (V2V), a framework that discovers genetic associations without subjective phenotype engineering.1/7

[David Kelley @drklly]

The application includes a short research proposal — if you're interested but want to talk through ideas before writing it up, feel free to email me. I'm happy to chat about what directions would be a good fit.

[David Kelley @drklly]

We're hiring a postdoc in my group at @calico! We develop deep learning methods for regulatory genomics to predict how every nucleotide in the genome affects cell-type-specific gene regulation.

[David Kelley @drklly]

You'd be joining a small, focused group where you'll have real ownership of your research direction. If this sounds like your kind of problem, or you know someone it'd be perfect for, apply or share the link: https://t.co/fri9k0EWyJ

[Han Yuan @HY3952]

Join us at Calico in Summer 2026 to work on challenging problems in regulatory genomics, using sequence models to better understand gene regulation and genetic variation. Apply if you are interested! https://t.co/qlvg3o2cky

[David Kelley @drklly]

If this sounds interesting, apply here https://t.co/OULz7ZZ9x2 with a brief cover letter describing your background and what draws you to this work. Deadline is Feb 1, 2026; position runs 3 months over summer 2026 in South San Francisco.

[David Kelley @drklly]

My group at Calico is looking for a summer intern. We develop machine learning methods to understand gene regulation—how sequence determines expression, how variants alter function, and what human genetics can tell us about aging.

[David Kelley @drklly]

We’re looking for someone with experience in ML and genomics (or strong in one and eager to learn the other) who wants to dig into real research questions, not just run existing pipelines.

[David Kelley @drklly]

Will this recipe work for other organisms? We think it depends on genome size and proportion of nucleotides under selection, which drives the value of the self-supervised stage and training data scale. An exciting question for future work!

[David Kelley @drklly]

Excited to share our new paper on predicting gene expression in yeast! We introduce "Shorkie," a supervised ML model that builds off a self-supervised foundation to interpret regulatory DNA.
Preprint: https://t.co/wyFJDokD6R

[David Kelley @drklly]

This was a massive effort, driven by the incredible work of Calico intern Kuan-Hao Chao (@KuanHaoChao). Huge thanks to him, Majed Mohamed Magzoub, and Johannes Linder (@jjohlin)!