Senior Backend Engineer - Scalable ML Inference (Golang)

Unity; Mountain View (CA); On-site; USD 210,000 - 273,000; Full time

Benefits offered by this job

Health insurance

Equity awards

Retirement/pension plans

Generous vacation and personal days

Parental leave support

Job summary

Unity is hiring for a backend engineering role focused on production-grade services powering online model inference at scale. You will design, deploy, and optimize low-latency, high-throughput infrastructure on GCP with Kubernetes, while partnering with ML engineers to handle increasing model complexity.

Strong observability with Prometheus/Grafana is essential. The role emphasizes DevOps/SRE practices, Docker-based microservices, and exposure to ML serving platforms.

Qualifications

• Experience designing, deploying, and maintaining distributed systems at scale.
• Expertise in Golang for high-performance backend infrastructure.
• Hands-on experience with GCP and workload orchestration using Kubernetes.
• Solid grounding in monitoring/observability with Prometheus and Grafana.
• Experience in ad tech, recommender systems, real-time personalization, or similar domains.
• Familiarity with microservice architectures, Docker, and CI/CD practices.
• Familiarity with ML platforms, workflows, and serving infrastructure.

Responsibilities

• Design, develop, and deploy production-grade backend services and distributed systems.
• Lead technical direction of inference platform for low-latency serving.
• Collaborate with ML engineers to scale online serving with growing models.
• Ensure reliability and efficiency using monitoring/observability tools.
• Manage cloud infrastructure on GCP and orchestrate workloads with Kubernetes.
• Promote best practices for backend development, testing, deployment, and monitoring.

Skills

Golang

Distributed systems

GCP

Kubernetes

Prometheus

Grafana

Docker

CI/CD

ML platforms

Tools

Terraform

Mesos/K8s tooling

Job description

Unity is hiring for a backend engineering role focused on production-grade services powering online model inference at scale. You will design, deploy, and optimize low-latency, high-throughput infrastructure on GCP with Kubernetes, while partnering with ML engineers to handle increasing model complexity.

Strong observability with Prometheus/Grafana is essential. The role emphasizes DevOps/SRE practices, Docker-based microservices, and exposure to ML serving platforms.