The Subvocal Company
Talk to your computer without talking
Head of ML
About the role
We are looking for the person who will own the central machine learning problem at Subvocal: turning weak, noisy, highly variable physiological signals into continuous language.
We have already built prototypes that decode subvocal speech at more than 200 words per minute. The much harder problem now is generalization. A model that works on one person, in one session, with one device placement is not a product. It needs to work when the same person returns the next day, when the hardware moves slightly, and eventually when a completely new person puts it on and gives us only a few minutes of calibration data.
You will lead that effort end to end. You will work directly with the founders and our sensing and hardware leads to decide what data we collect, how we represent the signal, which model families we pursue, and how we evaluate whether we are actually making progress.
Some of the problems you will work on include:
- Learning general representations from large amounts of unlabeled and weakly labeled physiological time-series data.
- Building continuous sequence models using approaches such as Conformers, Mamba-style architectures, CTC, transducers, and pretrained speech or language models.
- Separating speech-related information from anatomy, placement, session, device, and environmental variation.
- Adapting a large cross-user model to a new person from roughly 15 minutes of calibration data.
- Designing honest user-held-out, session-held-out, and device-held-out evaluations.
- Scaling training across thousands of hours and thousands of people.
- Getting the complete system to run continuously with low enough latency for real-time use.
Our current ML stack is primarily Python, PyTorch, CUDA, and distributed GPU training, with custom infrastructure for signal processing, data collection, experiment tracking, and evaluation.
You might be a great fit if you have unusually strong experience in deep learning for speech (ASR), time series, biosignals, neuroscience, BCIs, radar, or another domain where signals are noisy and data distributions shift constantly. We are especially interested in people with PhD-level research ability, whether or not that came through a formal PhD, who are also comfortable writing production-quality code and moving quickly when the research direction changes.
This is not a role where you will be handed a model architecture and asked to improve it incrementally. You will help decide how the problem should be framed in the first place, build the initial ML organization around you, and directly determine whether this technology becomes a real product.
This is a full-time, in-person role in San Francisco.
About The Subvocal Company
The Subvocal Company (YC F26) is building a wearable that lets you communicate with computers without speaking out loud.
Our goal is to turn deliberate subvocal speech, words you form internally without producing an audible voice or overt movement, into text and commands. Imagine writing an email, coding, searching the web, or talking to an AI at the speed of speech while sitting in a quiet office, on a train, or in the middle of a meeting, without anyone around you hearing a word or seeing you do anything.
Making this work requires solving an unusually difficult sensing and machine learning problem. The broader technical design space includes RF sensing, EMG, EEG, mmWave, and other non-invasive physiological sensing methods. For competitive and IP reasons, we are not publicly disclosing the exact architecture of our current system yet. What we can say is that we have already built prototypes that decode continuous subvocal speech at 200+ words per minute with high accuracy from real physiological signals, and we are now turning that research into a portable device that can work across people after a short calibration.
We are a small team in San Francisco, backed by Y Combinator and Afore Capital, along with some incredible angels. We move extremely quickly, build most things from first principles, and work across sensing, machine learning, embedded systems, hardware, and product design. The people joining now will not be optimizing a mature product or working on one narrow subsystem. They will help make foundational technical decisions, own entire areas of the company, and shape what this interface ultimately becomes.
We think silent speech will become a new fundamental way humans interact with computers. If working on something that still sounds slightly like science fiction, but is rapidly becoming a real engineering problem, sounds exciting to you, we would love to hear from you.
