🛠 Tech Stack

💼 About This Role

You'll design and develop scalable backend services for large-scale inference systems at Unity Ads. You'll own the performance, reliability, and scalability of services that power advertising models. This role collaborates closely with ML research and product teams to build critical infrastructure.

🎯 What You'll Do

• Design and deploy scalable backend services for large-scale model inference.
• Maintain system reliability and observability with Prometheus and Grafana.
• Collaborate with data science and product teams to align platform capabilities.
• Manage cloud infrastructure on GCP and orchestrate workloads with Kubernetes.

📋 Requirements

• Strong experience with large-scale distributed systems on GCP with Kubernetes.
• Expertise in Golang for high-performance low-latency systems.
• Experience with monitoring tools like Prometheus and Grafana.
• Familiarity with microservices, Docker, and CI/CD practices.

✨ Nice to Have

• Experience with NVIDIA Triton Inference Server.
• Ad tech or real-time personalization background.
• Mentorship and collaborative culture contribution.