Guard-Ex is developing a state-of-the-art impairment detection device. The Data Scientist will be responsible for designing and implementing groundbreaking solutions utilizing large-scale data sets. As we accelerate our analytics capabilities, we are looking for passionate problem solvers to develop innovative solutions that ultimately aid the law enforcement to make an accurate impairment decision through Data Science and AI. You will be working closely with optometrists, computer vision experts, software developers, hardware developers and other senior team members to design, build, validate, refine, and operationalize predictive models. You will also be involved in directing system testing and validation procedures, and also working with data scientists, hardware engineers and software developers on technical issues including software system design and maintenance.
Innovative and Dynamic - No Cubicles here!
- Analyze and compare the ranges of different data variability patterns of an individual’s physiological signs.
- Competent in Data Mining, Data Infrastructure, Data Interpretation & Communication, Decision Analysis, Data Wrangling.
- Familiar with Machine Learning methods.
- Able to deal with imperfections, outlying data, include missing values, inconsistent string formatting and data formatting.
- This individual is also responsible for conducting research using the latest AI/ML techniques, coordination & collaboration with various internal teams, and working closely with engineering to integrate solutions into our production systems.
- Multivariable Calculus & Linear Algebra - improvements in predictive performance, algorithm optimization.
- Apply your expertise in quantitative analysis to create and scale insights.
- Compile timely, comprehensive and accurate documentation and or reports as requested
Technical & Computer Skills
- Enhanced the platform’s mapping engine to facilitate through thousands of variable databases of different vital signs in seconds with real-time image processing to make decisions.
- Experience in a Linux/Unix environment, with Git, AWS, or APIs through co-op or school programs is considered an asset.
- Ability to develop statistical tests and run controlled trials.
- At least two years experience of advanced programming skills in one or more of the following languages: Python, R, Scala.
- Knowledge of Parallel Programming and High Performance Computing.
- Knowledge of general Machine Learning concepts (both in theory and application) and experience with advanced topics (including Probabilistic Graphical Models [convolutional nets, autoencoders, etc] Sequence Labeling [RNN and LSTM], Manifold Learning [encoding and dimensionality reduction of non-Gaussian data], and Semi-supervised Learning).
- Experience with Natural Language Processing, Feature and Representation learning, and Anomaly/Outlier Detection [both parametric and non-parametric].
- Masters degree/PhD in a quantitative discipline such as Computer Engineering/Science, Statistics, Machine Learning, Applied Math, or equivalent work experience.
Organizational Culture Asymmetry
- Have a great attitude and are proven self-starters.
- Willing to learn new technologies.
- Thrive and ability to function in a rapidly changing environment.
- Results oriented and deadline driven.
Communication & Collaborative Skills
- Excellent verbal and written communication skills.
- Driving innovation
- Continious Integration
Our Data Scientists are client facing with an ability to understand complex business problems, and how to solve those problems by leveraging analytics applied on client and 3rd party data. The Data Scientist’s job is to also make the solution “real”, by integrating it into business processes. Finding in those process points for automation of decisions and process through Artificial Intelligence. If you like big data, dream in neural nets, and you thrive on always finding new ways to grow as a company - we want to hear from you.