Machine Learning Engineer

South San Francisco - SSFfull time

Remote

$129k–$331k

H1B: yes

Neuralink Machine Learning Engineer at Neuralink working on decoding neural signals for virtual arm control and brain-to-voice synthesis. Responsibilities include training models on neural spike data, designing online adaptation, compressing decoders for low latency, and building voice synthesis stacks.

Responsibilities

In January 2024, a man paralyzed below the shoulders received a Neuralink implant. Within days he was playing chess and Civilization VI by imagining a cursor moving. That was our first product experience: computer control decoded from 1,024 electrodes in the brain’s motor cortex.
Since then, 20+ people have been using the device, some for 17+ hours per day.
We are now working on two problems nobody has solved.
Decoding the full virtual arm. This requires deciphering 29 degrees of freedom against millisecond timescale neural spikes. The published state of the art is four degrees of individuated finger control (Willsey et al., Nature Medicine 2025). We aim to fully decipher human intent of controlling anything that a human hand is capable of doing, and build a product that our users rely on for their independence every day.
Brain to voice. The frontier of real-time voice synthesis from intracortical signals is intelligible roughly half the time and carries only coarse pitch control (Wairagkar et al., Nature, 2025). We are working towards prosodic speech, in users’ own voices, streaming fast enough to hold a natural conversation.
If you want to help us solve these problems, we want to hear from you.
Why this is an interesting machine learning problem
Data. Train on >50,000 hours of neural data from clinical trial participants
Nonstationarity. Tackle the tough open problem that neural activity drifts and we need to solve decoding while minimizing user recalibration
Co-adaptation. The brain adapts to your decoder while your decoder adapts to the brain
Strict constraints. The brain implant operates on a tight power and the participant experience requires optimizing every millisecond of latency
Your eval is a person. Success is a human being capable of doing something today that they couldn't do yesterday