Remote Senior ML Infra Engineer — Real-Time Model Serving

3M HEALTHCARE; Mountain View (CA); On-site; USD 183,700 - 248,600; Full time

Benefits offered by this job

Health insurance

Stock options

Retirement plan

Generous time off

Job summary

Unity is seeking a Senior Machine Learning Infrastructure Engineer for the Vector Ads team. You will design, build, and operate real-time ML model serving infrastructure that powers Unity’s ads ecosystem, ensuring low latency and high throughput at global scale.

You will collaborate with ML engineers to productionize models, manage deployments, and improve system observability and cost efficiency in a remote-first setting.

Qualifications

• Experience building and operating ML infrastructure or model serving systems in production.
• Proficiency in Golang or Python.
• Hands-on experience with Kubernetes at scale.
• Familiarity with ML serving frameworks (Ray Serve, Triton, TorchServe).
• Understanding of distributed systems, API design, and system reliability.
• Strong collaboration and communication in a remote-first environment.

Responsibilities

• Design, build, and maintain ML model serving infrastructure in real-time across Unity’s ads ecosystem.
• Own latency, throughput, and reliability of serving pipelines in a high-QPS environment.
• Collaborate with ML engineers to productionize models and manage deployments.
• Improve observability, performance, and cost-efficiency of ML serving infra.
• Contribute to architectural decisions around feature serving and inference optimization.

Skills

Golang

Python

Kubernetes

ML serving frameworks

Distributed systems

API design

Collaboration

Tools

Ray Serve

Triton

TorchServe

Terraform

Prometheus

Grafana

OpenTelemetry

Job description

Unity is seeking a Senior Machine Learning Infrastructure Engineer for the Vector Ads team. You will design, build, and operate real-time ML model serving infrastructure that powers Unity’s ads ecosystem, ensuring low latency and high throughput at global scale.

You will collaborate with ML engineers to productionize models, manage deployments, and improve system observability and cost efficiency in a remote-first setting.