- Integrate into a small, high-ownership squad where you own the full lifecycle (design, implement, deploy, monitor, and iterate) with direct impact on revenue-critical systems processing millions of bid requests per second.
- Lead the design and architecture of backend services that power real-time model inference and bidding decisions for our OpenRTB platform.
- Collaborate with data scientists and machine learning engineers to deploy, monitor, and optimize ML models that influence real-time bidding strategies, pricing decisions, and targeting - including potentially developing proprietary models in-house.
- Oversee the development of A/B testing frameworks and ensure the seamless integration of experimentation tools into our platform for continuous model and bidding optimization.
- Ensure that all backend services are high-performance, low-latency, and scalable, capable of handling large data volumes (millions of bidding events per second).
- Set best practices for architecture, API design, and distributed systems to ensure robust and maintainable systems at scale.
- Work with the cloud infrastructure teams to ensure efficient deployment, scaling, and monitoring of backend services using Kubernetes, Docker, and CI/CD pipelines.
- Work closely with product managers to define and implement new features, optimizations, and improvements to the bidding and model inference system.
- Lead efforts to optimize performance and cost-efficiency across the backend infrastructure, ensuring that the system can scale effectively with increasing traffic and data.
- Continuously monitor the system’s performance, perform post-deployment analysis, and make improvements based on real-world usage and A/B test results.
AWSDockerPython+8 more