Staff/Principal Machine Learning Engineer

Epia Neuro•Alameda, CA

9d•Hybrid

About The Position

Epia Neuro is a neural technology company developing intent-driven systems that restore function and independence for people living with neurological conditions. Our platform integrates implantable neural interfaces, adaptive algorithms, and assistive devices to translate neural intent into real-world action. Our initial focus is stroke-related motor impairment, with planned expansion into cognitive decline and other neurological disorders. The Role We have a strong research group driving early brain-computer-interface (BCI) algorithm development. We are looking for someone with deep, hands-on BCI machine learning (ML) expertise to own neural decoding and carry it from validated research approaches to real-time algorithms running in human clinical studies. This is where applied BCI work gets real: your models decode intent from actual participants, under the constraints of a live clinical program. This is a senior individual-contributor leadership role, open at the Staff or Principal level depending on skills and experience. You will set ML technical strategy across decoder design, the decoding platform, and system architecture. Your focus is neural decoding, but your influence won't stop there: you will help raise the bar for ML engineering and modeling practices across the company. You will stay hands-on, working closely with our research team and with Software, Firmware, Hardware, and Robotics. How We Work We are intentional. We prioritize and are thoughtful about how we use others' time. We care for others. We prioritize safety both for patients and one another. We own outcomes, not just tasks. Our work demands the highest standards because it impacts real patients and real lives. Humility is a strength. We are honest about what we know and what we don't know. Getting it right matters more than being right.

Requirements

PhD in computational neuroscience, machine learning, or a related field is expected.
4-8+ years developing and deploying BCI algorithms in an industry or product setting, with a track record of owning technical direction at a scope that spans teams.
Production-quality Python and strong software engineering fundamentals, including testing, code review, and maintainable design in a collaborative codebase.
Deep expertise in neural signal processing and real-time, closed-loop decoding, calibration, and adaptation.
A working understanding of the practical constraints and failure modes of real BCI clinical trials.
Excellent communication and cross-functional collaboration skills.

Nice To Haves

Direct experience leading neural decoding through an end-to-end human clinical deployment.
PhD or postdoctoral training in a leading neural prosthetics, motor systems, or BCI research lab.
Proficiency in C++ or embedded development for an inference runtime, and edge or on-device ML.
Familiarity with safety-critical or regulated systems, such as medical devices (IEC 62304, ISO 13485, design controls).

Responsibilities

Own ML technical strategy for neural decoding, from validated approaches through real-time algorithms deployed in human clinical studies, spanning decoder design, the decoding platform, and system architecture.
Define data collection, labeling, and evaluation protocols for neural and behavioral data, and set performance criteria tied to clinical use.
Contribute to long-term BCI and machine learning platform strategy.
Partner with our research team to take neural decoding approaches from concept through validated prototype, including model design, training, and evaluation.
Develop and improve real-time, closed-loop decoding of neural intent, including online calibration, decoder adaptation, and robustness over time.
Own productization of the decoding algorithms, taking validated approaches to a deployable real-time inference runtime that meets latency and power budgets on the device.
Own integration of decoding models into the broader medical device product across Software, Firmware, Hardware, and Robotics.
Lead the ML side of human clinical study deployment, accounting for signal non-stationarity, session-to-session variability, limited participant time, and clinical-trial safety and regulatory constraints.
Lead debugging and root-cause analysis across the ML, firmware, and controls boundaries.
Set ML engineering standards, documentation practices, and test methodologies within our regulated software lifecycle, and review the work of other engineers against them.
Mentor engineers across the ML function and strengthen the team's technical depth.
Represent ML technical positions in regulatory strategy, partner discussions, and work with scientific advisors.