Startup Spotlight: Dipole Labs builds optical switches to keep AI cluster traffic in light
Harvard postdocs Deepankur Thureja and Gabriele Pasquale are turning photonics research into reconfigurable networking hardware for GPU fleets.
By RuntimeWire Staff · Published
Primary source: Y Combinator
Why it matters
AI infrastructure spending increasingly depends on extracting more work from installed accelerators. Dipole is betting that workload-aware optical switching can improve utilization without adding another row of GPUs.
Deepankur Thureja and Gabriele Pasquale are building Dipole Labs around an expensive piece of dead time inside AI clusters: processors waiting for the network to deliver data.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.