Computational Neuroscientist

Wispr is building a more natural way to interact with technology with neural interfaces. We have an elite team of engineers, product designers, and research scientists building magic.

About Wispr: We've raised $26.5M from top-tier VCs like NEA and 8VC. Our angels and advisors include Chester Chipperfield (product lead for the first Apple Watch), Ben Jones (COO, CTRL-Labs), Dave Gilboa (CEO, Warby Parker), and Jose Carmena (Berkeley professor; co-CEO iota). Our founders are Stanford alums and have previously sold a company and run a team at a deep tech startup with over 100M in funding.

As a member of our computational neuroscience team, your primary responsibilities will be to design, implement, and improve algorithms to process surface electromyography (EMG) and other neural signals. You will lead the experimental design, data collection, and infrastructure development to iterate on experiments rapidly.

Come join us and make magic happen.

Core Job Responsibilities

• Design and run research/engineering experiments for decoding intent from electro-physiological signals, such as EMG
• Leverage domain knowledge in human speech physiology, motor unit action potential decoding, etc, to build scientifically-grounded machine learning & computational models
• Implement data collection frameworks, curate datasets, perform pre-processing/feature extraction, and build machine learning models for EMG decoding
• Work with electrical & mechanical engineers to design systems like custom electrodes and analog circuits
• In addition to core R&D tasks, develop independent ideas for building a more natural way to interact with technology

Required Knowledge/Skills, Education, And Experience

• Ph.D. in neuroscience, biomedical engineering, electrical engineering, machine learning, or a closely related discipline
• 2+ years of work experience with electro-physiological time series data
• Experience in electrophysiology: EEG, EMG, or intra-cortical BCI (analysis and de-noising)
• Published academic research in peer-reviewed journals
• Software engineering skills for machine learning experiments, including experience in Python
• Experience working collaboratively with teams and good communication

Nice to have Knowledge/Skills, Education, And Experience

• Prior work in motor unit action potential decoding from EMG
• Familiarity with machine learning and data science packages such as PyTorch and Pandas
• Experience with consumer wearables
• Experience with computational models to process neural signals / bio-signals in real-world environments
• Software engineering best practices, including comfort with Linux environments and git version control

Why Wispr?
• Build magic and see the excitement spark in every users' eyes
• Design the next generation of personal computing in a creative, innovative, and collaborative environment
• Do the best work of your life with a world-class team
• Flexible work arrangements to support you in working in the way that you work best

For full-time employees:
• Generous health, dental, and vision coverage
• Generous parental leave, unlimited PTO (we encourage taking days off!)
• 401k match
• Commuter benefits
• Relocation assistance
• Total compensation for this position may also include stock options and other potential future incentives

At Wispr, diversity is important to us.

At Wispr, we believe that true innovation starts with people from diverse backgrounds coming together, bridging ideas, and collaborating. Wispr is proud to be an Equal Employment Opportunity employer and is committed to providing an environment of mutual respect where employment opportunities are available to all applicants and teammates without regard to race, color, religion, sex, pregnancy (including childbirth, lactation, and related medical conditions), national origin, age, physical and mental disability, marital status, sexual orientation, gender identity, gender expression, genetic information (including characteristics and testing), military and veteran status, and any other characteristic protected by applicable law.