Job Details

Meta is seeking Research Scientists with experience in product-focused signal processing and machine learning to help us create novel wearable sensors and algorithms to power the next generation of neuromotor interfaces and augmented reality systems. Help us unleash human potential by removing the bottlenecks between user intent and action.

Qualifications: Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience Ph.D. in machine learning, AI, computer science, electrical engineering, statistics, applied mathematics, data science, signal processing, optimization or related technical fields Proven track record of publication demonstrating experience in research Research-oriented software engineering skills (SciPy ecosystem/ML tools, MATLAB) Experience with human-in-loop sensor development (e.g. biosensors or novel input devices such as electrocardiography (EKG/ECG), photoplethysmography (PPG), capacitive sensing, electromyography, etc) Statistically grounded design of test methods for evaluating sensor hardware performance in lab and factory (e.g. aggressor studies and simulations, hardware phantoms) Demonstrated experience of statistical signal processing skills Experience working in consumer hardware engineering Experience building user interaction systems and/or working in human-computer interaction Experience shipping consumer hardware products at large scale Experience defining research/technical direction for a team and to support the work of a small group of researchers towards those goals

Responsibilities: Collaborating with hardware and machine learning teams to define sensor performance requirements as well as characterize the dependencies between sensors and overall system performance Exploring and designing new sensing architectures and characterizing their impact on the downstream ML models and their requirements Building simulation tools and use them to explore sensor performance Developing methodologies and tools to simulate biophysical signals and their approximations