Senior ML Infra Engineer - Scalable Online Inference

Unity; Oregon; On-site; USD 165,000 - 273,000; Full time

Benefits offered by this job

Health insurance

Stock ownership

Retirement plan

Generous vacation

Parental leave

Job summary

Unity is seeking a Senior ML engineer to design and evolve Unity Vector’s online model inference platform. You will build reliable infrastructure for serving ML models in production, optimize inference performance, and enable safe experimentation across high-traffic systems.

You will work with ML engineers, platform teams, and product stakeholders to deploy, scale, monitor, and iterate on models. The role requires strong systems thinking, deep production ML infrastructure experience, and the

Qualifications

• Experience building and operating production-grade online ML inference systems.
• Strong experience with distributed systems and Kubernetes.
• Strong programming skills in Python.
• Experience with PyTorch and model deployment workflows.
• Experience designing infrastructure for safe model rollout and canary testing.

Responsibilities

• Design and operate large-scale online inference infrastructure with low latency and high reliability.
• Develop infrastructure for distributed training workflows and orchestration.
• Integrate ML pipelines with workflow systems to enable reliable multi-stage training.
• Improve observability with latency, throughput, and model-health monitoring.
• Lead architectural improvements for a robust, scalable platform.

Skills

Python

PyTorch

Kubernetes

Ray

Distributed systems

Model serving

Tools

NVIDIA Triton Inference Server

TorchServe

Ray Serve

TensorFlow Serving

Flyte

Airflow

Job description

Unity is seeking a Senior ML engineer to design and evolve Unity Vector’s online model inference platform. You will build reliable infrastructure for serving ML models in production, optimize inference performance, and enable safe experimentation across high-traffic systems.

You will work with ML engineers, platform teams, and product stakeholders to deploy, scale, monitor, and iterate on models. The role requires strong systems thinking, deep production ML infrastructure experience, and the