Speaker

DJ Seo

DJ Seo

Engineering lead at Neuralink, where he has worked since the company’s early years on the N1 implant, the R1 surgical robot, and the biophysics underpinning both. Trained as an electrical engineer, he moved from millimetre-wave telecom circuit design into biomedical engineering during a PhD at UC Berkeley’s Berkeley Wireless Research Center, working under Professor Michel Maharbiz on neural dust — neuron-sized wireless sensors powered and read out by ultrasound rather than radio waves. Neuralink itself did not adopt the neural-dust approach, choosing wired flexible threads instead, but the underlying biophysics problem — how to extract a usable signal from tissue at the scale of a single neuron — carries directly into his work on the N1.

Core positions

Seo’s central engineering argument is that flexible, thin electrodes beat rigid ones because brain tissue actively punishes rigidity: older devices such as the Utah array provoke a scarring immune response (via microglia and astrocytes) that progressively pushes surviving neurons away from a fixed electrode, the field’s dominant long-term failure mode. Neuralink’s threads, by contrast, move with the pulsing brain rather than against it — histology from a seven-month implant shows neurons sitting directly against the threads with no visible scarring.

He frames Neuralink’s safety case around histology as the gold standard (‘the language… FDA speaks’), and its ambition around vertical integration: building its own fabrication, laser milling, and surgical robot in-house because no off-the-shelf device or surgical practice can handle threads this fine, and because serving the scale of patients he envisions — ‘a real possibility that you could see 8 billion people walking around with Neuralink’ — exceeds what a limited supply of neurosurgeons could ever deliver one procedure at a time.

In the wiki