Staff Machine Learning Engineer - Game Tech Group, ML Platform
Core
Architecting and scaling the shared ML infrastructure (model serving, orchestration, feature management) to move AI systems from experimentation to reliable production services across Riot's game development and player experience teams.
Role type
Staff Machine Learning Engineer (ML Platform Infrastructure)
Builds
Shared ML infrastructure including model serving, orchestration, feature management, and deployment workflows for Riot's AI ecosystem.
Domain
Gaming / Machine Learning Infrastructure / MLOps
Deliverable
infrastructure
Required skills
ML/AI platform engineering, inference serving (KServe, Triton, TorchServe), GPU orchestration, CI/CD, infrastructure-as-code (Terraform), distributed systems architecture
Preferred skills
Real-time/latency-sensitive ML deployment, LLM/diffusion model optimization, agentic workflow orchestration
Technologies
KServe, Feast, Milvus, NVIDIA Triton, Dynamo, TorchServe, Terraform
Responsibilities
Design and operate AI & ML inference infrastructure with CPU/GPU-aware orchestration; Develop CI/CD workflows for safe promotion to production; Optimize infrastructure for varied model architectures (foundation models, gradient boosted trees); Establish ML deployment best practices (blue/green, shadow deployments); Improve developer experience by reducing operational complexity; Influence long-term platform architecture; Collaborate with researchers and game teams to build reusable platform capabilities.
Seniority
Staff, hands-on IC with strategic influence
