Senior ML Engineer
Core
Design and architect backend services for real-time model inference and bidding decisions in an OpenRTB platform, optimizing advertising strategies and targeting.
Role type
Senior backend engineer specializing in real-time ML inference systems
Builds
High-performance, low-latency backend services for real-time bidding (RTB) and model inference
Domain
Mobile gaming advertising, real-time bidding, distributed systems
Deliverable
production ML models | product features | infrastructure
Required skills
Python, distributed systems, microservices, API design, Kubernetes, Docker, CI/CD, Terraform, observability (Prometheus, Grafana), A/B testing frameworks, performance tuning, cost optimization
Preferred skills
OpenRTB protocols, real-time data processing (Kafka, Pub/Sub), model serving frameworks (Triton, TorchServe, Ray Serve), data science workflows, open-source contributions
Technologies
Python, Kubernetes, Docker, Terraform, Prometheus, Grafana, Kafka, AWS, OpenRTB
Responsibilities
Lead design and architecture of backend services for real-time model inference; Collaborate with data scientists to deploy and optimize ML models for bidding strategies; Oversee development of A/B testing frameworks; Ensure high-performance, scalable backend services handling millions of events; Set best practices for architecture and distributed systems; Optimize performance and cost-efficiency of backend infrastructure; Monitor system performance and conduct post-deployment analysis
Seniority
Senior, hands-on IC
