BCI Engineer

BCI Engineer

Stealth Research Lab · Cambridge, MA (in-office) · Full-time

We are a team of neuroscientists, mathematicians, physicists, computer scientists, AI researchers, and engineers on a mission to learn from the human brain and to build an AI that can learn continuously, in a sample-efficient way, and reason about its knowledge. We are a seed stage team with early commercial traction building Cortex. Cortex is in use by customers today, and we’re only just beginning in terms of research and capabilities.

We’re looking for a brain-computer interface (BCI) engineer to build the bridge between real neural activity and Cortex. You’ll design and run the systems that acquire, clean, and decode neural signals, and you’ll use that data to test our brain-inspired ideas against the brain itself instead of against analogies. You’ll help make neural data a first-class input to how we design, train, and evaluate Cortex.

Your near-term focus will be on real-time neural signal processing pipelines, decoding models across recording modalities (EEG, ECoG/sEEG, intracortical arrays, fMRI, spikes and LFP), curating and standardizing public and partner datasets, and using neural recordings to constrain and evaluate the representations Cortex learns. The company is also evaluating their own portable non-invasive BCI device, on which you will be involved as well. 

Longer-horizon goals we expect you to participate in include closed-loop systems where Cortex and neural recordings interact in real time, foundation models trained on neural data, and benchmarks grounded in how biological systems actually learn and remember. We expect to push the envelope from “interdisciplinary” work to “a new, named field of science” and you will be part of it.

As a BCI Engineer, you’ll bring both engineering rigor and scientific judgment. You’ll work with our neuroscientists and research engineers to design experiments and analyses, and with our engineers to turn what works into reliable infrastructure. Your primary outputs will be production-quality systems and code, with publications and technical reports where the work earns them, roughly a 60/40 split.

• Build and own end-to-end neural data pipelines: acquisition, synchronization, preprocessing, feature extraction, and storage in standard formats.
• Develop and benchmark neural decoders, from classical baselines to modern deep learning approaches, across invasive and non-invasive modalities.
• Build low-latency, real-time systems for streaming neural data and running models in closed loop, with clear latency and reliability budgets.
• Use neural recordings to test hypotheses about learning, memory, and knowledge representation, and translate the findings into concrete design choices for Cortex.
• Curate, clean, and harmonize large public and partner neural datasets, and build the tooling that lets the rest of the team use them quickly and correctly.
• Help design new benchmarks and evaluations that compare how Cortex and biological systems learn, represent, and use knowledge.
• Work with academic and clinical partners on data sharing, experiment design, and the practical constraints of working with human neural data.
• Author technical reports and papers, and help shape our neural data and BCI strategy.

• Have a track record in neuro-engineering, biomedical or electrical engineering, computational neuroscience, machine learning, physics, or another quantitative field, through shipped systems, publications, or both.
• Have hands-on experience working with neural recordings such as EEG, ECoG, sEEG, fMRI, or intracortical spikes and LFP, and know their failure modes firsthand.
• Have strong signal processing foundations: filtering, spectral and time-frequency analysis, artifact handling, and the statistics needed to tell signal from noise.
• Have trained and evaluated machine learning models on neural or other time-series data, for example using PyTorch.
• Write excellent production software in Python, and are comfortable in a systems language such as C or Rust when latency matters.
• Have built real-time or streaming systems and care about latency, timing, and synchronization across devices.
• Have strong experimental discipline: careful baselines, ablations, held-out sessions and subjects, and honest reporting of negative results.
• Communicate beautifully in writing and proactively in conversation. Most problems are not technical and we need you to help solve those ones too.
• Are curious about how biological learning works, and want to turn those ideas into working systems.

• Published BCI or neural decoding research, for example in motor, speech, or memory decoding, at venues such as NeurIPS, the IEEE EMBS Neural Engineering conference, or the Journal of Neural Engineering.
• Experience with human intracranial or intracortical data in clinical or research settings, including IRB processes and data privacy requirements.
• Hardware or firmware experience with neural acquisition systems, such as amplifiers, headsets, or implant interfaces, and the bench skills that come with it.
• Experience with large-scale neural foundation models or self-supervised learning on neural data.
• A computational neuroscience background in areas like hippocampal function, complementary learning systems, consolidation, or predictive coding.
• Experience owning software that holds up in high-stakes environments, with the reliability habits (monitoring, testing, safe rollouts) that come with real users.
• Familiarity with medical device development, such as design controls or FDA regulatory pathways.

We’re looking for exceptional people, and we know few candidates will match every line above. If this is the work you want to do and some of it describes you, take a shot and apply. Pedigree and experience checkboxes often push away underrepresented groups and just generally outsiders of all stripes. That’s not what we’re trying to do. We’re signaling that we expect the best and we care about the quality of your thinking. This space is exciting because only the quality of our ideas and execution bottlenecks us.

equal opportunity employer.