Design, build, and operate high-throughput, low-latency ad-serving infrastructure processing millions of requests per second. Optimize GPU-powered TensorRT inference, feature stores, model serving, benchmarking, experimentation tooling, and system reliability. Partner with machine learning engineers to productionize models and own systems through design, deployment, observability, capacity planning, incident response, and optimization.

Design, implement, and maintain partner integration solutions; translate partner requirements into scalable technical implementations; troubleshoot and automate fixes; collaborate with product and engineering teams to improve tools and ensure successful partner onboarding and launches.