Platform Architect

The Role:

• Set the standard for building, shipping, and operating ML and AI systems at scale.
• Tackle hard problems: model serving reliability, inference cost and latency, reproducible pipelines, and agentic workload operations.

What You'll Work On:

• Build and operate model and inference serving infrastructure with a focus on latency, throughput, autoscaling, and reliability.
• Own the ML deployment lifecycle including model registry, versioning, promotion workflows, and rollout strategies.
• Operate agentic and LLM workloads in production, managing inference providers, gateways, quotas, and guardrails.

Must Have:

• 5+ years in platform engineering, SRE, MLOps, or infrastructure with production systems.
• Deep Terraform and Kubernetes expertise with hands-on GKE and multi-project GCP experience.
• Strong automation-first mindset and experience with agentic coding tools.