Senior ML Inference Platform Engineer

Unity Technologies SF; United States; On-site; USD 210,000 - 273,000; Full time

Benefits offered by this job

Comprehensive health, life, and disabl

Commute subsidy

Employee stock ownership

Competitive retirement plans

Generous vacation and personal days

Parental leave support

Office snacks

Job summary

Unity Technologies SF 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 online systems.

You will collaborate with ML engineers and platform teams to ensure scalable deployment, monitoring, and iteration of models, shaping packaging, validation, and deployment automation in production

Qualifications

• Experience operating production-grade online ML inference systems (e.g., Triton, TorchServe, Ray Serve, TensorFlow Serving).
• Strong Python programming experience in production ML systems and high-scale services.
• Experience with distributed systems, Kubernetes, autoscaling and observability.
• Experience designing infrastructure for safe model rollout, canary testing and AB testing.

Responsibilities

• Design and operate large-scale online inference infrastructure for production ML models with low latency and high reliability.
• Develop infra for distributed training workflows using PyTorch, Ray Data, and Ray Train.
• Integrate ML pipelines with workflow systems like Flyte and Airflow to enable multi-stage training.
• Optimize model performance via compilation, GPU/CPU utilization, scheduling, and runtime tuning.
• Improve observability including latency, throughput, errors, and cost monitoring.
• Collaborate with ML engineers to accelerate model iteration while preserving safety and scale.
• Lead improvements for packaging, validation, deployment automation, and reproducibility.

Skills

ML infra

Python

Kubernetes

PyTorch

Model serving

Canary testing

Latency optimization

Tools

Triton Inference Server

TorchServe

Ray Serve

TensorFlow Serving

Kubernetes

Job description

Unity Technologies SF 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 online systems.

You will collaborate with ML engineers and platform teams to ensure scalable deployment, monitoring, and iteration of models, shaping packaging, validation, and deployment automation in production