Staff Backend Engineer, Real-Time ML Inference

LE130 Unity Technologies SF; Mountain View (CA); On-site; USD 193,000 - 318,000; Full time

Benefits offered by this job

Health insurance

Stock ownership

Retirement plans

Vacation and personal days

Parental leave

Office snacks

Mental health programs

Employee Resource Groups

Global Employee Assistance Program

Training and development programs

Volunteer matching program

Job summary

Unity Technologies is seeking a Staff Backend Engineer to design, build, and operate distributed systems powering large-scale model inference in the Vector Gamer AI team. You will focus on low-latency, high-throughput backend services and cloud infrastructure on GCP, with Kubernetes across a high-scale production environment.

You will collaborate with ML engineers to scale inference workloads, implement observability with Prometheus and Grafana, and promote DevOps/SRE practices to improve

Qualifications

• 5+ years designing distributed systems at scale.
• Expertise in Golang for high-performance backend infrastructure.
• Hands-on experience with GCP and Kubernetes.
• Strong grounding in monitoring and observability with Prometheus and Grafana.
• Experience in ad tech, recommender systems, or real-time personalization.

Responsibilities

• Design, develop, and deploy production-grade backend services and distributed systems powering large-scale online model inference.
• Drive technical direction of the inference platform with focus on low-latency, high-throughput serving infrastructure.
• Partner with ML engineers to scale online serving infrastructure with growing model complexity and inference volumes.
• Ensure reliability, scalability, and efficiency using monitoring/observability tools.
• Manage and optimize cloud infrastructure on GCP with Kubernetes across a high-scale production environment.
• Promote and implement backend DevOps/SRE practices.

Skills

Distributed systems design

Golang

Cloud infrastructure (GCP)

Monitoring & observability

Ad tech / real-time personalization

Microservices architecture

CI/CD practices

ML inference platforms

NVIDIA Triton Inference Server

Tools

Kubernetes

Docker

Prometheus

Grafana

NVIDIA Triton Inference Server

Job description

Unity Technologies is seeking a Staff Backend Engineer to design, build, and operate distributed systems powering large-scale model inference in the Vector Gamer AI team. You will focus on low-latency, high-throughput backend services and cloud infrastructure on GCP, with Kubernetes across a high-scale production environment.

You will collaborate with ML engineers to scale inference workloads, implement observability with Prometheus and Grafana, and promote DevOps/SRE practices to improve