Description

You will design and operate scalable AI infrastructure, focusing on model serving, GPU orchestration, and cost optimization.

This role is remote.

Responsibilities

• Build and manage vector database infrastructure for RAG and retrieval workloads, handling indexing, sharding, and performance tuning.
• Implement end-to-end observability for LLM and agent workloads, including metrics, tracing, logging, and latency/cost dashboards.
• Develop CI/CD and MLOps pipelines to ensure reproducible model deployments with safe rollouts and rollback capabilities.
• Ensure reliability, security, and compliance across the entire AI serving stack.
• Partner with ML and agent engineers to remove infrastructure bottlenecks and improve developer velocity.

Required Skills

• 10+ years of experience in Platform Engineering, Infrastructure Engineering, DevOps, or MLOps.
• Strong proficiency in Kubernetes and Docker for container orchestration.
• Hands-on experience with cloud platforms (AWS, GCP, or Azure).
• Experience with model serving technologies such as vLLM, Triton, TGI, or similar inference optimization tools.
• Operational experience with vector databases like Pinecone, Weaviate, pgvector, or Milvus.
• Solid skills in Infrastructure-as-Code (IaC) practices and Python programming.
• Experience building CI/CD pipelines for ML workloads.

Preferred Skills

• Experience with GPU cluster management and cost/performance optimization at scale.
• Background in supporting production LLM and AI agent workloads.
• Security and compliance experience specific to AI systems.

Key Skills

Education

Bachelor's degree