- Experience
- 3+ yrs
- Salary
- —
- Openings
- 1
- Posted
- 1 week ago
- Work mode
- Work from home
- Resume
- Required to apply
Sign in to tell us what does and doesn't work for you here — it sharpens every match we show you.
Job description
Overview
This opportunity is offered on behalf of a partner company based in Ireland seeking a Data Scientist. The role involves building and refining sophisticated machine-learning models that handle terabytes of data to support billions of real-time advertising requests globally. You will be engaged in the full lifecycle of data science tasks, spanning research, exploration, model design, and deployment.
Responsibilities
- Create and optimize machine-learning products from initial experimentation to production deployment.
- Enhance models by integrating new features, parameter tuning, and utilizing diverse data sources.
- Work collaboratively with machine learning engineering teams to implement scalable supervised and unsupervised algorithms.
- Investigate data sources to uncover improvement opportunities for models and insights.
- Research innovative machine-learning techniques to improve various facets of the advertising product lifecycle.
- Design and evaluate A/B tests to validate assumptions and quantify the impact on products and models.
- Apply algorithms for tasks like prediction, clustering, and anomaly detection on large-scale sparse datasets.
- Develop dashboards and SQL-based tools to monitor model and product outcomes.
- Write clean, maintainable, well-tested code contributing to robust data science workflows.
- Collaborate with diverse teams to translate complex issues into scalable solutions focused on business value.
- Maintain focus on practical impact ensuring machine learning efforts deliver measurable benefits.
Qualifications
- Minimum three years of relevant experience creating data science solutions from research stages to production.
- Proficient in writing clean, reproducible, and well-tested code.
- Advanced skills in Python, Spark, Hadoop, Airflow, Docker, and SQL.
- Experience with algorithms suited for sparse, large-scale datasets, including prediction, clustering, and outlier detection.
- Solid understanding of data evaluation, experimentation, and statistical methods including A/B test design and interpretation.
- Previous experience within the Ad-Tech sector is mandatory.
- Familiarity with production use of Gradient Boosting Trees such as CatBoost or LightGBM is advantageous.
- Experience with neural networks for classification, regression, or multi-task learning highly valued.
- Knowledge of reinforcement learning and large-scale optimization is a strong plus.
- Comfortable building and using dashboard and SQL monitoring tools.
- Excellent communication and teamwork capabilities across various technical and non-technical teams.
- Preference for straightforward, impactful solutions avoiding unnecessary complexity.
- Curiosity and eagerness to experiment and continually improve models.
- Ability to thrive in a diverse, international, remote working environment.
Benefits
- Direct interaction with company founders and opportunities to influence product and strategic directions.
- Strong prospects for professional growth and ongoing learning.
- Collaboration with seasoned professionals shaping the future of Ad-Tech worldwide.
- Work within a multinational, motivated, and geographically distributed team.
- Fully remote work option with flexible arrangements and opportunity to relocate to Berlin office.
- Home office setup budget of $500 and a $1,000 annual budget for learning and development.
- Engagement with large-scale machine learning systems handling massive datasets and real-time advertising data.
- International, collaborative environment encouraging innovation, experimentation, and ownership.
Skills
Tools & software
Docker
· 2 to 5 years required
Apache Airflow
required
Apache Hadoop
required
How they work
Communication
Teamwork & Collaboration
Learning Agility
Results Orientation