We Are Hiring!

Responsibilities

• You will develop processes and pipelines for state-of-the-art brain- and biosignal processing and analysis (EEG, NIRS, ExG, eye tracking and others) for a variety of study and statistical designs, both for post-hoc analysis and real-time uses.
• Most of your work will be on workflows used in production by clients, in Intheon’s products (NeuroPype, NeuroScale), and in in-house R&D, and will leverage the Python ecosystem, with occasional limited use of MATLAB or R tools.
• Working with an interdisciplinary team, you will continuously expand your skill set and bridge between neuroscience, statistics, signal processing, machine learning and other disciplines, follow current research and findings in the neurosciences, and help distill these findings into a new generation of automated, robust, and large-scale processing suites for brain- and biosignal data.
• You will also advise on and contribute to experimental designs for neuroscience research and validation studies (in-house or in collaboration with clients and partners).
• You will contribute to the extension of Intheon’s software stack and product platform through the development, implementation, and validation / testing of published and pre-publication methods.

Professional Requirements

• Doctorate (Ph.D.) degree, or Master’s (M.S.) degree with equivalent years of experience, in one of Cognitive Science, Computational Neuroscience, Electrical Engineering / Computer Science, Statistics, Theoretical Physics, or a related field.0
• Excellent communication skills, ability to self-manage projects, and motivated team player.
• A desire to thrive and grow in a fast-paced and challenging high-tech startup environment working on advanced research projects.
• Professional conduct respecting HIPAA and other applicable regulations, as well as confidentiality requirements of Intheon’s customers and partners.
• Commitment to maintaining an open, welcoming, harassment-free, and equal-opportunity workplace.

Technical Requirements

Required skills:

• Demonstrated solid knowledge of neuroscientific principles, conceptual models, and current literature. Track record of peer-reviewed scientific publications.
• Familiarity with current-generation neural data analysis techniques, particularly related to electrophysiology (e.g., spectral analysis, source estimation / localization, functional / effective connectivity, multi-subject analysis, artifact removal).
• Familiarity with the current ecosystem of neural data formats (e.g., time-series data, head models, atlases) and tools (e.g., FreeSurfer, Brainstorm, EEGLAB, etc.).
• Demonstrated solid understanding of, and prior experience working with, various general-purpose signal processing techniques (e.g., filter designs, spectral analysis methods, linear component analysis methods).
• Firm understanding of the inner workings, assumptions, and applicable range of various statistical models, including commonly-used frequentist and Bayesian models, and demonstrated experience applying such models. Comfortable applying statistical validation techniques and criteria.
• Solid grounding in common human-subject experiment paradigms and experiment design principles for eliciting neural or behavioral responses.
• Solid programming skills (clean, well-documented and well-tested code).
• Prior experience working with Python data science tools (e.g., numpy, scipy, pandas, matplotlib, jupyter, statsmodels, etc.).
• Excellent problem-solving skills, knack for abstract mathematical thinking (e.g., vector/matrix/tensor data, high-dimensional spaces, probability distributions, etc.).
• Excellent English verbal and written communication skills.
• High-quality clear writing for contributions to scientific manuscripts, technical reports, technical documentation, and user guides.
• Able and willing to fill any knowledge gaps quickly and to learn the necessary theory and tools.

Preferred skills / pluses:

• Experience working with optical (e.g., fNIRS), invasive (e.g., ECoG, microarray), fMRI, or other neural or non-neural data modalities a plus.
• Ability to read/write MATLAB code (R code a plus).
• Understanding of and prior experience applying hierarchical Bayesian models, related estimation/inference techniques (samplers, variational Bayes, etc.) and popular tools (e.g., Stan, PyMC3, etc.).
• Familiarity with adaptive/online statistical signal processing and the underlying principles (e.g., RLS, Kalman filters, etc.).
• Familiarity with sparse signal processing / modeling (e.g., compressive sensing, structured sparsity).
• Willing to learn or already familiar with high-performance computing tools and techniques in Python (e.g., cupy, jax, dask). Julia familiarity a plus.
• Familiarity with the fundamentals of machine learning (overfitting, cross-validation, regularization / priors, optimization, etc.).
• 2+ years of postdoctoral or equivalent research experience.