From TIME · · 1m 10s
How Lilly's AI Chief Built a Drug-Making Supercomputer
Diogo Rau transformed Eli Lilly's approach to medicine by deploying AI and computing power at every stage of drug development.
In brief
Diogo Rau transformed Eli Lilly's approach to medicine by deploying AI and computing power at every stage of drug development. Pharmaceutical companies are shifting drug discovery and manufacturing from wet labs to computational systems, fundamentally changing what scientists do. Originally reported by TIME.
Lilly's new supercomputer
Eli Lilly built LillyPod, an Nvidia-powered supercomputer with over 1,000 Blackwell GPUs, in just four months under chief information officer Diogo Rau's leadership.
Screening molecules faster
LillyPod now models biological processes and screens potential drug molecules before they enter wet lab experiments, accelerating early-stage discovery.
Manufacturing gets smarter
Rau's team built an AI digital twin of a production bottleneck, testing temperature and pressure variables virtually to shave minutes from critical processes.
Real impact on output
The digital twin initiative enabled a very large increase in units produced, with enough material impact on earnings to justify the investment.
The future of science
Rau believes drug-making itself is becoming computational, and that the shift will fundamentally change what being a scientist means in practice over the next decade.
“I don't think anybody thinks that in 10 years we'll have just as many scientists working in wet labs.”
The bottom line
Pharmaceutical companies are shifting drug discovery and manufacturing from wet labs to computational systems, fundamentally changing what scientists do.
