Senior Data Scientist
Compass
full-time
Posted on:
Location Type: Remote
Location: Brazil
Visit company websiteExplore more
Job Level
About the role
- Develop and evaluate classification models, monitoring performance metrics;
- Apply techniques for handling data imbalance and feature engineering;
- Work with large-scale transactional and financial data;
- Use MLflow and Unity Catalog for model versioning, traceability, and governance;
- Perform versioning, validation, and promotion of models across environments;
- Deploy models to production through Model Serving;
- Optimize hyperparameters and calibrate thresholds according to business rules;
- Process large-scale data using Spark (Spark SQL and PySpark);
- Automate training and deployment pipelines;
- Version projects and source code using GitLab;
- Develop machine learning solutions on the Databricks platform.
Requirements
- Strong knowledge in Data Science, Statistics, and Machine Learning;
- Experience in model productionization, including modeling, metric definition, performance evaluation, and ML solution governance;
- Proficiency in Python, SQL, and Spark for data analysis, processing, and manipulation;
- Experience in validation, homologation, and evaluation processes for analytical solutions;
- Experience with AWS cloud services;
- Collaborative profile, focused on knowledge sharing and enabling other data scientists.
Applicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard skills
classification modelsdata imbalance handlingfeature engineeringmodel versioningmodel validationmodel promotionhyperparameter optimizationdata processingmachine learning solutionsdata analysis
Soft skills
collaborationknowledge sharingenabling others