ShanX Medtech BV (SXM, NL) is a dynamic young company dedicated to revolutionizing healthcare through innovative diagnostic tools. Our journey began with a deeply personal experience—the founder's mother's near-fatal struggle with a poorly treated bacterial infection. This ignited our mission to transform infection management, propelling us to develop pioneering solutions that prevent unnecessary suffering.
At SXM, impact is paramount. We're proud to introduce KAIROS IVD, our groundbreaking rapid antibiotic susceptibility testing device, poised to redefine how bacterial infections are treated. Our goal is clear: to equip healthcare professionals with the means to make informed treatment decisions swiftly and accurately. Through our innovative solutions, we're combating antibiotic resistance, enhancing patient outcomes, and saving lives.
As a (Data) Scientist at SXM you will be responsible for the generation and development of new data analysis tools and algorithms. The role of the (Data) Scientist is pivotal in leveraging data-driven approaches to inform and accelerate diagnostic product development, ultimately leading to improved patient outcomes and healthcare delivery.
This is a part-time contract for 32 hours per week, extending over three years, with the possibility of extension and potential for an increased work week.
Your responsibilities include, but are not limited to:
Conducting R&D: Contribution to the generation of relevant data that will be
used as an input to (training of) algorithms.
Data Analysis: Leading the analysis of large and complex datasets, including
clinical data, and reference data generated from diagnostic assays. Applying
statistical (e.g. PCA) and machine learning techniques to extract insights, identify
patterns, and uncover relationships that inform diagnostic product development.
Algorithm Development: Training, developing and refining algorithms and
models for data analysis, interpretation, and predictive analytics. This may
involve designing algorithms for diagnosis and more, risk prediction, or treatment
response prediction to support diagnostic assay development but also
implementation in application software.
Feature Engineering: Identifying and engineering relevant features from raw data
to enhance the performance and accuracy of (predictive) models. This includes
preprocessing data, selecting informative features, and optimizing feature
representations for improved model performance.
Model Validation: Validating (predictive) models and algorithms using
appropriate validation techniques, including cross-validation, bootstrapping, and
holdout validation. Assessing model performance metrics such as accuracy,
sensitivity, specificity, and area under the curve (AUC) to evaluate predictive
performance.
Data Visualization: Creating clear and informative data visualizations, including
plots, charts, and graphs, to communicate results and insights effectively to
stakeholders. Visualizing complex data structures and relationships to facilitate
understanding and decision-making.
Continuous Learning: Staying abreast of advances in data science methodologies,
techniques, and tools relevant to in-vitro diagnostics. Actively participating in
professional development activities, such as training programs, conferences, and
workshops, to enhance skills and knowledge.
• Master’s degree in data science, Computer Science, Statistics, Bioinformatics, Biomedical Engineering, or a related discipline.
• 2 years’ experience in a similar function
• Proficiency in programming languages commonly used in data science such as Python, R, or SQL. The ability to write efficient code for data manipulation, analysis, and modeling is necessary.
• Familiarity with data management and preprocessing techniques, including data cleaning, transformation, and normalization.
• Machine Learning: Basic understanding of machine learning concepts and algorithms, including supervised and unsupervised learning, classification, regression, clustering, and dimensionality reduction.
• Ability to create clear and informative data visualizations using tools like Matplotlib, Seaborn, or ggplot2. Proficiency in conveying complex data insights through charts, graphs, and dashboards is important.
• Fluency in English.
• Openness to learn about performing experimental work in a laboratory environment and with bacteria.
• Transferring algorithms and communication to professional application software developers. Maintain algorithm integrity/performance.
• Experience with machine learning libraries such as scikit-learn or TensorFlow is beneficial.
• Experience with handling large-scale datasets and databases is advantageous.
• Domain Knowledge: Familiarity with the fundamentals of in-vitro diagnostics, including knowledge of biomarkers, assay technologies, and clinical applications. Understanding basic microbiology and medical terminology is advantageous.
• Good communication skills to non-technical stakeholders
• A passion for working in a young company environment.
• Competitive compensation and benefits package
• Access to professional development opportunities for career growth and advancement, including training resources.
• Flexible schedule and work arrangements
• Dynamic and collaborative work environment
Join us in shaping the future of healthcare, where every moment is vital in the fight against bacterial infections. We're seeking a motivated (Data) Scientist to join our team and contribute to the development of this crucial diagnostic device. This is an exceptional opportunity to join us in our early stages and play a pivotal role in our future success.