Senior Machine Learning Engineer, ML Infrastructure- Online

Unity Technologies SF is hiring a Senior Machine Learning Engineer to design and evolve Unity Vector’s online model inference platform. The role focuses on dependable, low-latency production serving, performance optimization, observability, and controlled experimentation.

Responsibilities

• Design and operate large-scale online inference infrastructure that serves production machine learning models with low latency and high reliability, including systems such as PyTorch, Triton Inference Server, Kubernetes, GKE, Ray, or comparable distributed serving frameworks.
• Build infrastructure to support distributed training workflows using technologies such as Pytorch, Ray Data, and Ray Train.
• Integrate machine learning pipelines with workflow orchestration systems such as Flyte, Airflow, or similar tools to enable reliable multi-stage training workflows.
• Optimize model performance through techniques including 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 rates, cost, saturation, and model health.
• Work closely with ML engineers to accelerate model iteration while maintaining production safety, scalability, and cost efficiency.
• Improve reliability and reproducibility of model serving workflows, including 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.

Requirements

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

Technologies

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

Location

Olympia, WA (onsite)

Compensation

USD 165,600 - 273,400 per year

• Zone A: $210,300 - $273,400
• Zone B: $187,200 - $243,300
• Zone C: $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