First seen by Alion on Nov 16, 2026.
About the Role
We are looking for an experienced Data Scientist to join a team developing data driven solutions in the cybersecurity industry.
In this role, you will combine machine learning, data processing, and software engineering to build reliable solutions. You will work with complex datasets and help bring machine learning models into production.
Responsibilities
Develop, train, and optimize machine learning models, including anomaly detection, using scikit-learn and XGBoost.
Process and transform large datasets in Python (e.g. Polars, PyArrow) and build feature engineering and data validation workflows.
Work with AWS data services (S3, Athena, Glue) and write SQL for data access.
Package and manage models with MLflow, with artifacts stored on S3.
Collaborate with engineering teams to integrate ML solutions into production systems.
Requirements
Professional experience in Data Science or Machine Learning.
Strong Python skills, including data processing libraries.
Hands-on experience with scikit-learn (e.g. Random Forest, Isolation Forest) and XGBoost.
Good knowledge of SQL and experience with structured datasets.
Experience with AWS (S3, Athena, Glue) and MLflow or similar model management tools.
Solid understanding of feature engineering, model evaluation, and data validation.
Strong problem-solving skills and the ability to work independently
Nice to Have
Experience with Polars, PyArrow, boto3, or awswrangler.
Experience with MLflow PythonModel and model artifacts on S3.
Experience with Jinja-templated SQL.
Background in cybersecurity data or anomaly detection systems.
What We Offer
Fully remote cooperation within the EU.
Work on meaningful, data-driven projects in the cybersecurity space.
A chance to build ML solutions that go into real production systems.
Collaboration with an experienced, supportive engineering team.
Room for professional growth and learning new technologies.
Tech stack
- Machine Learning
- Python
- AWS

