Senior ML Infra Engineer — Scalable Inference & Platform

Unity Technologies; Seattle (WA); On-site; USD 187,000 - 243,000; Full time

Job summary

Unity Technologies in Seattle is seeking a Senior ML Engineer to design and evolve Unity Vector’s online model inference platform. You will build reliable production infrastructure for serving ML models with low latency and high reliability, and enable safe experimentation at scale.

You will work closely with ML engineers, platform teams, and product stakeholders to ensure models can be deployed, scaled, monitored, and iterated on efficiently.

Qualifications

• Experience building and operating production-grade online ML inference systems.
• Experience with model serving frameworks such as Triton, TorchServe, Ray Serve, or TensorFlow Serving.
• Experience optimizing inference workloads (dynamic batching, quantization, GPU acceleration, kernel tuning).
• Strong experience with distributed systems, Kubernetes, autoscaling, and production observability.
• Strong Python programming skills for production ML systems.
• Experience with PyTorch and model packaging, validation, and serving lifecycle management.
• Experience designing infrastructure for safe model rollout, canary testing, and automated rollback.
• Ability to reason about latency, throughput, reliability, and cost tradeoffs in online systems.

Responsibilities

• Design and operate large-scale online inference infrastructure with low latency and high reliability.
• Develop infrastructure supporting distributed training workflows (e.g., PyTorch, Ray Data, Ray Train).
• Integrate ML pipelines with workflow orchestration (Flyte, Airflow) for multi-stage training workflows.
• Optimize model performance via compilation, GPU/CPU utilization, scheduling, and kernel fusion.
• Improve observability of ML systems (latency, throughput, error-rate, cost, model-health).
• Collaborate with ML engineers to accelerate model iteration while ensuring safety and scalability.
• Improve reliability and reproducibility of serving workflows (packaging, validation, deployment automation).
• Lead architectural improvements to make the platform robust and cost-efficient.

Skills

Production ML infra

Distributed systems

System design

Observability

Performance optimization

Leadership (influence)

Tools

NVIDIA Triton Inference Server

TorchServe

Ray Serve

TensorFlow Serving

Kubernetes

Python

PyTorch

Flyte/Airflow

Job description

Unity Technologies in Seattle is seeking a Senior ML Engineer to design and evolve Unity Vector’s online model inference platform. You will build reliable production infrastructure for serving ML models with low latency and high reliability, and enable safe experimentation at scale.

You will work closely with ML engineers, platform teams, and product stakeholders to ensure models can be deployed, scaled, monitored, and iterated on efficiently.