Unity
Staff Backend Engineer, Vector AI
$193K–$318K
Mountain View, CA, USA · Staff · Full-time · Posted Sep 28, 2026
- Experience
- 5+ years designing, deploying, and maintaining distributed systems at scale.
About the job
Build and operate high-scale backend and distributed systems for low-latency online ad-model inference and bidding decisions.
What you'll do
- Design, develop, and deploy backend services and distributed systems for billions of daily model-inference requests.
- Set technical direction for low-latency, high-throughput inference infrastructure and work with ML engineers to scale online serving.
- Operate and optimize production systems on GCP and Kubernetes, using observability tools and backend development, testing, and deployment practices.
What they ask for
- 5+ years designing, deploying, and maintaining distributed systems at scale.
- Expertise in Golang for high-performance, low-latency backend infrastructure.
- Hands-on experience with GCP and Kubernetes.
- Experience with monitoring and observability tools, including Prometheus and Grafana.
Nice to have
- Experience with NVIDIA Triton Inference Server.
- Familiarity with auction mechanics or ad-tech bidding systems.
Pay
$192,600 - $317,800 USD annual base salary
Tools
Golang, GCP, Kubernetes, Prometheus, Grafana, Docker, NVIDIA Triton Inference Server
AI focus
Build and operate infrastructure for large-scale online machine-learning inference, partnering with ML engineers to support increasingly complex models and inference volumes.
Model-written summary · the original posting is authoritative