View job on Handshake
LifeQ is seeking a dynamic and experienced Data Scientist to be part of the Science team.
LifeQ provides a fast-paced and dynamic work environment with access to industry-leading technology and collaboration with influential international corporations. Employees enjoy a comfortable office environment with benefits such as a gym, a fully equipped kitchen and amazing coffee!
The ideal candidate will be someone with an enthusiasm for first-principle thinking, great interpersonal skills, a willingness to learn and adapt to new challenges, and a drive for developing innovative products that will launch the company forward.
Job Description
This position requires a strong drive to develop a quantitative understanding of the latest developments in public health studies and published models and to translate this knowledge into innovative algorithms and research outputs. The Data Scientist will work in interdisciplinary teams on projects including a wide range of models and algorithms, using existing data and data forthcoming from pilot initiatives. These projects will involve extracting relevant physiological, behavioral, and environmental information from technology including smart watches and other gold standard monitoring equipment, and producing models from extracted features in order to predict health and wellness outcomes (e.g. stress or disease risk) or characterize behavioral choices (e.g. exercise).
For some projects, the applicant may be tasked with reviewing and upgrading existing models by adding new data, employing new algorithms, or applying new learnings made in the relevant field(s). Research and development work must be conducted following a well-designed scientific process with the final goal of implementing the solution according to a product specification. Long term success in this role will also include the ability and interest to help define the scope and nature of deliverable products.
The Data Scientist will report to the Science Team leads and the company’s Chief Scientist.
Responsibilities
Research
- Develop data driven models in support of research objectives.
- Capability to support model development through various levels of product maturity. This ranges from initial stages where model parameters are derived from the scientific literature, to mature stages where training involves thousands of datasets.
- Follow proper scientific methodology to validate algorithms/models, both new and old (e.g. measuring quantitative performance statistics, testing assumptions and limitations, assessing bias and variance of models, etc.).
- Clearly capture and document learnings made during the research and development process, both for internal knowledge sharing and in public-facing documents (e.g. white papers).
- Contribute to the productization of the models, i.e. envision how the model outputs can be packaged and presented to users, anticipate and resolve possible friction points from a user’s perspective, and assist with user education.
- Produce relevant technical specification documents for models.
- Participate in study design for relevant projects.
- When applicable, contribute to the development of intellectual property filings.
Software Development
- Create and maintain any code produced for models, algorithms, or data analysis on internal repositories.
- Follow best practices relating to collaborative coding and version control.
Competence Development
- Continuously improve relevant skills to meet the evolving demands of novel projects.
- Build on multi-disciplinary knowledge to enable teamwork and collaboration with various teams within the organization.
Skills
Candidates with a M.S. or Doctorate level education, and/or at least 3 years experience in relevant technical roles, are invited to apply if they hold any of the following qualifications:
- A background in machine learning or data science.
- A background in statistics, mathematics and/or applied mathematics.
- A background in bioengineering, biological modeling and/or computational systems biology.
General programming experience is required, including at least a basic comfort in Python.
Additional experience/skills which will carry extra weight in the application include:
- Experience/skill in data science related work (feature engineering, modeling, predictive analytics, etc.), particularly in cloud environments.
- Experience/skill in applying machine learning techniques (e.g. Neural Networks, Support Vector Machines, Random Forests).
- Experience/skill in ordinary differential equation-based modelling.
- Experience/skill in analyzing time series data, and/or digital signal processing (frequency domain analysis).
- Experience in using software version control methods (e.g. Git repositories).
- Experience/skill in using serverless computing platforms e.g. AWS Lambda.
- Experience/skill in connecting to external API data resources, such as those hosting digital health data.
- Experience/skill in biometrics and the understanding of concepts arising in public health studies.
- Experience with regulation and/or regulatory bodies e.g. the FDA.