[unemphysbro]

funny enough I'm doing the exact same thing in public sector education. I'm always curious where people in our field end-up.

i saw some of your other comments about being at google. did you touch jax-md at all?

https://github.com/google/jax-md

[dekhn]

I talked to the team, but unfortunately, jax-md at the ttime didn't do bond angles or torsions, so it wasn't good for biomolecular simulations.

My work mostly predated tensorflow and was much more about massive-scale embarassingly parallel computing, and produced some interesting large-scale results from MD and protein folding.

https://www.nature.com/articles/nchem.1821 https://onlinelibrary.wiley.com/doi/full/10.1002/pro.2389

[unemphysbro]

yup, i noticed that when i saw the first commits; in fact i thought it was someone's pet project. however, when i read that first odenet paper, it's clear keeping track of the gradients is extremely useful.

I'm very familiar with the first paper, the second author was on my committee.

so what does a cloud migration at a biotech company mean?

is it sort of a standard orchestrator + warehouse/lakehouse + distributed compute + cicd tools stack?