SOPHiA GENETICS

www.sophiagenetics.com

1 Job

501 Employees

About the Company

SOPHiA GENETICS was founded in 2011 by biologists who had a vision to create a technology that could make a positive and lasting impact on the world, using data for good.

We’ve built a revolutionary technology platform, SOPHiA DDM™, that rapidly distills complex data into actionable insights, enabling clinicians, researchers, and biopharma to reshape the way that we diagnose and treat cancer and rare inherited disorders.

The AI fueling our platform learns from the complex genomic and multimodal data provided by our community of users to create a collective intelligence over time. By using the power of data and AI, we are expanding access to data-driven medicine and enabling the patients of today to help the patients of tomorrow.

Our science is driven by unrelenting passion for our mission to transform patient care by expanding access to data-driven medicine globally.

We wouldn’t be able to achieve all that we have – and all that we will – without our people, who are driven by our shared purpose to ensure that every patient worldwide has equitable access to precision medicine.

Our virtues are our behaviors we exhibit every day, and our mantra “We Care” is our driving force.

Listed Jobs

Company Name: SOPHiA GENETICS
Job Title: Junior Data Scientist Intern
Job Description: **Job Title:** Junior Data Scientist Intern **Role Summary:** Intern responsible for developing and validating machine learning models that estimate heterogeneous treatment effects (HTEs) from real‑world oncology data. Works under the Multimodal Biostatistics Manager to support personalized treatment decision‑making in cancer care. **Expectations:** - Conduct comprehensive literature reviews on HTE methodologies and tools. - Prepare multimodal real‑world datasets for predictive modeling. - Train, validate, and evaluate ML models on oncology RWD. - Integrate selected models into a production pipeline. - Present analytical findings to interdisciplinary teams. **Key Responsibilities:** 1. Review current research and software libraries relevant to HTE estimation. 2. Clean, transform, and engineer features from multimodal clinical data. 3. Build and tune ML models (e.g., causal inference, ensemble, neural networks) to predict treatment effects. 4. Validate model performance using appropriate metrics and cross‑validation. 5. Package models for deployment within a factory‑style ecosystem. 6. Document methodologies, results, and insights; deliver presentations. **Required Skills:** - Strong statistical foundation in biostatistics or related fields. - Proficiency in machine learning concepts and applied Python (pandas, scikit‑learn, PyTorch/TensorFlow). - Experience with data manipulation, feature engineering, and model validation. - Familiarity with causal inference / treatment effect estimation techniques. - Excellent written and verbal communication in English. - Ability to work collaboratively yet independently on technical projects. **Required Education & Certifications:** - Current enrolment in a Master’s program in Biostatistics, Applied Statistics, Applied Mathematics, or a closely related discipline. - No additional certifications required.