Senior Machine Learning Engineer, ML Infrastructure- Online

Unity Technologies SF is hiring a Senior Machine Learning Engineer to help evolve Unity Vector’s online model inference platform. This role is centered on building production infrastructure that delivers low-latency, high-reliability inference, while strengthening optimization, observability, and safer experimentation workflows.

Based in Olympia, WA (onsite), you will work across ML infrastructure and systems to improve how models are served, measured, and rolled out in production.

What you’ll do

• Design and operate large-scale online inference infrastructure that serves production ML models with low latency and high reliability, using tools such as PyTorch, Triton Inference Server, Kubernetes, GKE, Ray, or similar distributed serving frameworks.
• Build infrastructure that supports distributed training workflows, including PyTorch, Ray Data, and Ray Train, among others.
• Integrate ML pipelines with workflow orchestration systems such as Flyte, Airflow, or similar platforms to support reliable multi-stage training.
• Optimize model performance through model compilation, GPU and CPU utilization improvements, request scheduling, kernel fusion, and runtime-level tuning.
• Enhance observability for ML systems by monitoring latency, throughput, error rate, cost, saturation, and model health.
• Partner with ML engineers to speed up model iteration while maintaining production safety, scalability, and cost efficiency.
• Improve reliability and reproducibility across serving workflows through model packaging, artifact validation, compatibility testing, and deployment automation.
• Lead architectural improvements to make the online ML platform more robust, user-friendly, scalable, and cost-efficient.

What you bring

• Experience building and operating production-grade online ML inference systems such as NVIDIA Triton Inference Server, TorchServe, Ray Serve, TensorFlow Serving, or similar systems.
• Hands-on experience with model serving frameworks including NVIDIA Triton Inference Server, TorchServe, Ray Serve, TensorFlow Serving, or similar.
• Proven ability to optimize inference workloads using approaches like dynamic batching, model compilation, quantization, GPU acceleration, GPU kernel optimization, caching, or runtime tuning.
• Strong background in distributed systems, including Kubernetes, autoscaling, service reliability, and production observability.
• Strong Python skills with practical experience supporting production ML systems and high-scale services.
• Experience with PyTorch and modern model deployment workflows, including model packaging, validation, and end-to-end serving lifecycle management.
• Experience designing infrastructure for safe rollout, including canary testing, A/B experimentation, and automated rollback.
• Systems thinking to evaluate latency, throughput, reliability, scalability, and cost tradeoffs.
• Demonstrated ability to lead technical direction and influence architectural decisions across teams without formal authority.

Technologies

• PyTorch
• NVIDIA Triton Inference Server
• Kubernetes
• GKE
• Ray
• Ray Data
• Ray Train
• Flyte
• Airflow
• TorchServe
• Ray Serve
• TensorFlow Serving
• Python

Compensation

• USD 165,600 - 273,400 per year
• Zone A: USD 210,300 - 273,400
• Zone B: USD 187,200 - 243,300
• Zone C: USD 165,600 - 215,200

Benefits

• Comprehensive health, life, and disability insurance
• Commute subsidy
• Employee stock ownership
• Competitive retirement/pension plans
• Generous vacation and personal days
• Support for new parents through leave and family-care programs
• Office food snacks
• Mental Health and Wellbeing programs and support
• Employee Resource Groups
• Global Employee Assistance Program
• Training and development programs
• Volunteering and donation matching program