About the Role

We’re looking for a curious, rigorous junior data scientist to help turn biosensor and clinical data into dependable, real world insights. You’ll contribute across the model lifecycle, from exploratory analysis and statistical validation to production ready pipelines, while collaborating closely with engineering, clinical, and product teams in a regulated environment. No prior MedTech experience needed, only strong problem-solving ability and adaptability in a rapidly changing company. Career changers and recent graduates are welcome to apply.

What You’ll Do (Key Responsibilities)

Learn and apply robust statistical techniques.
Profile complex, noisy datasets; perform analyses resilient to outliers, non normal distributions, and heteroscedasticity.
Apply inferential methods, confidence intervals, bootstrap techniques, and proper transformations; perform reliability/agreement assessments calibration, and ROC analysis for imbalanced data.
Employ machine learning techniques
Build supervised/unsupervised models in Python using scikit learn and related (pipelines, feature engineering, cross validation, hyperparameter tuning).
Evaluate models with task proper metrics, document assumptions, limitations, and risks.
Aid in the preparation of data sets.
Clean and transform time series/sensor and tabular clinical data; ensure traceability, reproducibility, and version control (Git).
Communication & teamwork
Present findings to technical and non technical stakeholders; write concise, well structured documentation.

Core Competencies (What Great Looks Like)

Knowledge of/desire to learn advanced statistical methods: Strong grasp of inferential statistics, effect sizes, confidence intervals, bootstrap, outlier resistant estimators, and agreement/validation frameworks for clinical measurements.
Python Ecosystem: Ability in Python, scikit learn, and common libraries (pandas, NumPy, SciPy, etc.).
Knowledge of/desire to learn ML Fundamentals: Solid understanding of supervised/unsupervised learning, feature engineering, cross validation, model selection, and generalization.
Data Handling: Practical skill in cleaning and transforming structured/unstructured data; comfort with messy real world sensor and clinical datasets.
Reproducible Research: Version control (Git), notebooks/scripts best practices, experiment tracking, and clear documentation.
Regulated Mindset: Awareness of data privacy, security, and medical device quality principles; ability to work within documented processes.
Communication: Ability to explain complex ideas clearly in writing and speech.

Qualifications

Degree in a quantitative field (Statistics, Data Science, Computer Science, Biomedical Engineering, Applied Mathematics, or similar).
PhD preferred (or equivalent experience) showing hands on quantitative analysis and scientific communication.

How You’ll Work

Collaborative: Under the guidance of the Data Scientist (Technical Lead), you will work closely with engineering, clinical, and product.
Evidenced: Decisions grounded in data, uncertainty quantification, and documented tradeoffs.
Iterative: Ship incremental improvements with clear experiment logs and QA checks.
User focused: Translate clinical/user needs into measurable goals and model requirements.

What We Offer

Mission driven work with real impact in healthcare.
Mentorship from experienced scientists and engineers.

Application Instructions

Please send:

Your CV (highlighting the above desired skills).
Optional) Links to code/notebooks or research outputs you’re proud of.

****Aboriginal and Torres Straight islanders as well as women are strongly encouraged to apply*****

VitalTrace

Company Overview