AI INFRASTRUCTURE ENGINEER — AGENTIC AI PLATFORM
Core
Design, build, and operate the infrastructure layer for an agentic AI platform, enabling low-latency inference, privacy-preserving data flows, and seamless transition between cloud and edge environments.
Role type
Lead Infrastructure Engineer (AI Platform)
Builds
CI/CD pipelines, AI workload infrastructure (LLM inference, embedding generation, vector search, RAG), Kubernetes clusters, observability systems, security/compliance infrastructure, and edge/on-device infrastructure.
Domain
Cloud infrastructure, AI/ML platforms, Edge computing
Deliverable
production ML models | infrastructure
Required skills
Kubernetes cluster management, Cloud provider expertise (GCP/AWS), Infrastructure as Code (Terraform, Helm, ArgoCD), AI workload optimization, Vector database management, Observability system design, Security and privacy infrastructure design, Edge/on-device inference planning.
Preferred skills
Multi-region deployment architecture, Encrypted data pipeline implementation, Transition strategy for cloud-to-edge compute.
Technologies
Kubernetes, GCP, AWS, Terraform, Helm, ArgoCD, Pinecone, Weaviate, pgvector, Cursor, Claude, Copilot.
Responsibilities
Design and operate CI/CD pipelines for distributed teams; Configure compute, networking, and storage for LLM inference and vector search; Manage and scale Kubernetes clusters with cost/latency tradeoffs; Build logging, metrics, and alerting systems; Enforce privacy-by-design architecture via encrypted pipelines and access controls; Plan and execute the transition from cloud-first to edge-first infrastructure.
Seniority
Senior, hands-on IC
