Unity
Senior Machine Learning Engineer, ML Infrastructure- Online
$166K–$273K
Remote, Washington, USA · Senior · Full-time · Posted Oct 7, 2026
About the job
Designs and operates Unity Vector’s online ML inference platform, improving production model serving performance, reliability, observability, and experimentation.
What you'll do
- Build and operate scalable online inference infrastructure and distributed training workflows, integrating ML pipelines with workflow orchestration systems.
- Optimize inference performance and improve monitoring, reliability, reproducibility, model deployment, and rollout safety.
- Lead platform architecture improvements and partner with ML engineers and other teams to support efficient model iteration.
What they ask for
- Experience building and operating production-grade online ML inference systems and model-serving frameworks.
- Strong experience with distributed systems, Kubernetes, autoscaling, reliability, and production observability.
- Strong Python programming skills and experience with PyTorch and production ML deployment workflows.
- Experience optimizing inference workloads and designing safe model rollouts, canary testing, A/B experimentation, and automated rollback.
Pay
Zone A: $210,300 - $273,400 USD base salary; Zone B: $187,200 - $243,300 USD base salary; Zone C: $165,600 - $215,200 USD base salary
Tools
PyTorch, Triton Inference Server, Kubernetes, GKE, Ray, Ray Data, Ray Train, Flyte
AI focus
Production ML infrastructure: online inference, distributed training workflows, inference optimization, and safe model experimentation and deployment.
Model-written summary · the original posting is authoritative