Senior Backend Engineer, Scalable ML Inference

Unity; Bellevue (WA); On-site; USD 166,000 - 273,000; Full time

Benefits offered by this job

Equity awards

Health insurance

Employee stock ownership

Competitive retirement plans

Generous vacation

Job summary

Unity is seeking a Senior Backend Engineer to design, build, and operate the distributed systems that power our Vector Gamer AI platform, processing billions of daily impressions and model inferences.

You'll own low-latency infrastructure, collaborate with ML engineers, and ensure reliability and scalability across GCP and Kubernetes, while promoting best-practices in DevOps and observability. The role may include equity awards and participation in incentive plans.

Qualifications

• Experience designing, deploying, and maintaining distributed systems at scale.
• Backend infrastructure with Golang and low latency.
• Cloud infrastructure on GCP and Kubernetes orchestration.
• Monitoring and observability with Prometheus and Grafana.
• Experience in ad tech 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 inference platform for low-latency serving infrastructure.
• Collaborate with ML engineers to scale complexity and inference volumes without latency.
• Ensure reliability and scalability using monitoring/observability tools.
• Manage and optimize cloud infrastructure on GCP with Kubernetes across a high-scale production environment.
• Promote best practices for backend development, testing, deployment, monitoring (DevOps, SRE).

Skills

Distributed systems

Golang

Microservices

Real-time processing

Latency optimization

Tools

Docker

Kubernetes

GCP

Prometheus

Grafana

NVIDIA Triton

Job description

Unity is seeking a Senior Backend Engineer to design, build, and operate the distributed systems that power our Vector Gamer AI platform, processing billions of daily impressions and model inferences.

You'll own low-latency infrastructure, collaborate with ML engineers, and ensure reliability and scalability across GCP and Kubernetes, while promoting best-practices in DevOps and observability. The role may include equity awards and participation in incentive plans.