Senior Backend Engineer, Vector AI

What you'll do

• Design and deploy backend services and distributed systems for billions of daily inference requests, focusing on low latency and high throughput.
• Set technical direction for the inference platform and collaborate with ML engineers to scale online serving as models and volumes grow.
• Manage GCP infrastructure and Kubernetes workloads, and maintain production reliability using monitoring, observability, and DevOps/SRE practices.

What they ask for

• Experience 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 in ad tech, recommender systems, real-time personalization, or another performance-critical domain; familiarity with Prometheus and Grafana is also requested.

Nice to have

• Experience with NVIDIA Triton Inference Server or other ML inference servers.
• Familiarity with auction mechanics or bidding systems in ad tech.

Pay

$165,600 - $273,400 USD (base salary)

Tools

Golang, GCP, Kubernetes, Prometheus, Grafana, Docker, CI/CD, NVIDIA Triton Inference Server

AI focus

Build and operate infrastructure for large-scale online model inference, including low-latency, high-throughput serving for ad ranking and bidding; partner with ML engineers to support growing model complexity and inference volumes.