About the Role
Design and deploy machine learning systems that enhance ad performance metrics by leveraging large-scale data and real-time optimization techniques.
Responsibilities
- Develop and maintain machine learning models to optimize digital advertising outcomes
- Collaborate with data scientists and engineers to integrate models into production environments
- Analyze large datasets to identify patterns affecting ad campaign performance
- Improve model accuracy through iterative experimentation and feature engineering
- Build data pipelines that support real-time decision-making in ad delivery
- Monitor model performance and implement updates to maintain effectiveness
- Work closely with product teams to align ML solutions with business goals
- Research new algorithms and techniques applicable to ad targeting and bidding
- Ensure models comply with privacy standards and data usage policies
- Document model design, training processes, and performance metrics
- Troubleshoot issues in model deployment and data flow pipelines
- Optimize inference speed and resource usage for low-latency environments
- Contribute to A/B testing frameworks for evaluating model impact
- Use statistical methods to validate model predictions against actual outcomes
- Support the scaling of ML infrastructure as data volume grows
- Participate in code reviews and maintain high software quality standards
- Stay current with advancements in machine learning and advertising technology
- Collaborate on cross-functional initiatives involving data governance and model transparency
- Design experiments to isolate causal effects in ad performance data
- Mentor junior engineers on best practices in machine learning engineering
Compensation
Competitive salary with performance-based incentives and comprehensive benefits package
Work Arrangement
Hybrid work model with flexible scheduling options
Team
Part of a specialized engineering team focused on advertising technology and data science integration
What We Value
- Technical excellence paired with practical problem-solving
- Ownership of projects from concept through deployment
- Clear communication across technical and non-technical roles
- Curiosity and initiative in identifying optimization opportunities
- Collaborative mindset with a focus on team success
Technology Stack
- Python for model development and scripting
- TensorFlow and PyTorch for deep learning applications
- Apache Spark for large-scale data processing
- AWS for cloud infrastructure and deployment
- Kubernetes for container orchestration
- Airflow for workflow automation
- BigQuery and Redshift for data storage and querying
- MLflow for model tracking and management
Visa sponsorship available for qualified candidates
