Job Summary:
Unity is looking for a Senior Machine Learning Infrastructure Engineer to join their Vector Ads team, where they build real-time systems for their global advertising platform. The role involves building and operating infrastructure for ML models, ensuring reliable performance at scale and collaborating with ML engineers to enhance model deployment processes.
Responsibilities:
โข Design, build, and maintain the infrastructure that serves ML models in real-time across Unity's ads ecosystem
โข Build and operate scalable model serving pipelines โ owning latency, throughput, and reliability in a high-QPS production environment
โข Partner with ML engineers to productionize models, manage model deployments, and improve iteration speed
โข Improve observability, performance, and cost-efficiency of ML serving infrastructure
โข Contribute to architectural decisions around feature serving, model versioning, and inference optimization
Qualifications:
Required:
โข Experience building and operating ML infrastructure or model serving systems in production
โข Proficiency in Golang or Python, with strong systems engineering fundamentals
โข Hands-on experience with Kubernetes and container orchestration at scale
โข Familiarity with ML serving frameworks such as Ray Serve, Triton, TorchServe, or similar
โข Understanding of distributed systems, API design, and system reliability
โข Strong collaboration and communication skills in a remote-first environment
Preferred:
โข Experience with feature stores, feature pipelines, or online/offline feature serving
โข Background in ad tech, real-time bidding, or programmatic advertising systems
โข Familiarity with infrastructure-as-code such as Terraform
โข Experience with observability tooling โ Prometheus, Grafana, OpenTelemetry
โข Background with real-time data pipelines, caching layers, or low-latency serving systems
Company:
Unity [NYSE: U] offers a suite of tools to create, market, and grow games and interactive experiences across all major platforms from mobile, PC, and console, to extended reality. Founded in 2004, the company is headquartered in San Francisco, USA, with a team of 5001-10000 employees. The company is currently Late Stage.