Data Scientist

AccuLine is a medical device startup founded in early 2022 with a vision to save the lives of millions of people worldwide by preventing the next heart attack.

AccuLine is developing CORA – a fast, accurate, non-invasive, inexpensive, and user-friendly examination for the early detection of coronary artery disease, aiming to replace inaccurate stress test exams. Our technology is based on the discovery of two bio signals in the heart’s electrical activity and deep learning analysis of several vital signs during a 4-minute exam. The exam can be performed easily by any medical staff personnel in any setting, and the results are provided immediately.

Position Overview

AccuLine is seeking an experienced individual to join our team as a Data Scientist. In this role, you will establish and shape data science and machine learning activities and play a pivotal role in the development of the core technology for CORA.

The data you will work with will include the unique time series data collected by the CORA device, alongside clinical and demographic data, and potentially large external public and private datasets. You will analyze this data using a variety of methods, including but not limited to classical machine learning methods and modern Deep Learning architectures.

Key Responsibilities:

• Report to the company's Chief Scientific Officer.
• Own the complete life cycle of machine learning models. This includes problem analysis, research / experiment definition, data preparation and exploration, model design, testing and validation, model deployment and refinement.
• Establish and utilize a cloud-based data science management platform.
• Create thorough documentation of model design, experiments, tests & validations.
• Support preparation of the ML aspects of future clinical & scientific publications.
• Support QA Audits conducted by external agencies.
• Work closely with other team members to understand ML adjacent topics – signal processing, clinical study design, and other data related activities in the company.
• Collaborate with external vendors to integrate data processes and ML models into the product.

Job Requirements

Must Have

• Advanced academic degree (preferably PhD) in Computer Science, Statistics, Data Science, or a related area.
• 5+ years of proven experience in leading end-to-end development of ML models, from initial research to production.
• Scientific writing skill in English.
• Experience in developing ML models for time series analysis.
• Deep grounding in applying ML techniques to biological / medical signals:

-'classical' regression and classification methods (linear, logistic, SVM, tree-based models, etc.)

-Deep Learning architectures – CNN, RNN, LSTM, Transformer, etc.

-Experience with TensorFlow, PyTorch, sci-kit learn, etc.

Strong Advantage

• Medical device industry experience.
• Biostatistics – including hierarchical modeling, Bayesian methods, power calculations.
• GPU / TPU coding experience.
• High coding proficiency in Python.
• Experience with code development workflows in a command-line linux environment.
• Proficiency in clustering and unsupervised learning methods.
• Experience with AWS or other cloud-based tools and technologies for data pipelining, model development and deployment.
• Experience with setting up and working with a data science management platform such as MLFlow, DVC, ClearML, etc.

We're looking for a collaborative, self-motivated candidate with a 'can-do' attitude for a fast-paced, entrepreneurial environment. Must be organized, detail-oriented, and able to communicate effectively at all levels of the organization