Data Scientist - Clinical

Penguin Ai

About The Position

This is a hands-on Data Scientist role focused on transforming real-world healthcare data into models and insights. The position involves close collaboration with the Clinical team to ensure the accuracy and relevance of the data. The role is not an independent architect position but offers opportunities to learn from senior data scientists and clinicians while taking ownership of analysis tasks. The core objective is to leverage skills in statistics, machine learning, and experimentation to drive impact through data. Responsibilities include problem framing, model building, and translating complex data into actionable stories for clinicians and stakeholders, ensuring all results are sound, reproducible, and clinically grounded. The ideal candidate thrives on finding patterns in data and values learning from healthcare professionals.

Requirements

4+ years of hands-on experience in data science or applied machine learning.
Experience in US Healthcare is essential.
Some experience helping take models or analyses from notebook to real-world use.
A track record of delivering analyses that informed real decisions.
Strong grasp of statistical methods, experimentation, and validation.
Hands-on experience building and tuning ML models (regression, tree-based methods, deep learning).
Comfortable with SQL and working with large, complex datasets.
Experience with key ML/data libraries (scikit-learn, pandas, NumPy).
Strong proficiency in Python and good software practices.
Good understanding of probability, statistical inference, and modern ML techniques.
Comfort with A/B testing, validation, and model evaluation.
Ability to translate business and clinical questions into analytical solutions and explain results plainly.
Strong problem-solving skills, a rigorous mindset, and a love of working with others.
A degree in Data Science, Statistics, Computer Science, Engineering, or a related field - or equivalent hands-on experience.

Nice To Haves

Clinical or EHR data experience.
Experience with PyTorch or TensorFlow.
Some exposure to cloud platforms (AWS, GCP, or Azure) and their data/ML services.
Experience with data visualization and BI tools (Tableau, Power BI, or similar).
Applied NLP techniques or large language models to real-world text.
Familiarity with AI safety, fairness, and responsible AI practices.
Experience with AI or automation projects that deliver measurable impact.
Experience in a high-growth startup environment.

Responsibilities

Build predictive and statistical models on real-world healthcare data with guidance from senior data scientists and clinical input.
Craft robust, production-ready models and pipelines that meet business and clinical objectives.
Support the design and analysis of A/B tests and studies, validating results against clinical reality.
Apply best practices for feature engineering, model selection, and validation.
Build and tune models (regression, gradient boosting, deep learning, NLP) for clinical and business use cases.
Design and implement reproducible data and training pipelines, plus evaluation frameworks.
Improve model accuracy, robustness, and cost for reliable production analytics.
Acquire, clean, and transform large, messy clinical and claims datasets using SQL and modern data tooling.
Partner with the Clinical team and clinical SMEs to understand workflows, define labels, and validate clinical sense of models.
Package models and analyses into reliable services and dashboards for clinical and operational decisions.
Support the accuracy, security, and reproducibility of models and analyses in production.
Translate business and clinical questions into precise, answerable data problems with stakeholders and clinicians.
Learn from senior data scientists and clinical experts, and share discoveries with the team.
Assess data quality and assumptions for new initiatives, flagging clinical and statistical risks.
Create clear visualizations, reports, and presentations to translate analysis into action.