DontApply.Club
Login Register

Generative AI DevOps Engineer

Ionixa Global — United States · Posted ~1 day ago

Mid

Skills

Cloud infrastructure Generative AI infrastructure Kubernetes Docker Terraform Infrastructure as Code CI/CD Vector databases RAG pipelines GPU/TPU optimization AWS Azure GCP OpenTofu CloudFormation LangChain LlamaIndex Semantic Kernel Pinecone Milvus Qdrant pgvector GitHub Actions GitLab CI Jenkins

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary

Build the cloud-native foundation for generative AI systems, from model training and serving to RAG pipelines. You will architect secure infrastructure, optimize expensive compute resources, manage Kubernetes and Docker workloads, implement Infrastructure as Code, and automate both software and model delivery.

Highlights

Technically advanced DevOps role focused on infrastructure for generative AI workloads, including model serving, RAG, vector databases, GPU/TPU optimization, cloud-native architecture, and automated deployment.

Description

Design and manage cloud infrastructure tailored for hosting, fine-tuning, and serving Generative AI models. Implement and manage infrastructure for AI orchestration frameworks (e.g., Lang Chain, Llama Index, Semantic Kernel). Optimize vector databases (e.g., Pinecone, Milvus, Qdrant, or pgvector in Postgre SQL) for highly efficient Retrieval-Augmented Generation (RAG) pipelines. Implement cost-optimization strategies for heavy compute resources (GPUs/TPUs). Architect, scale, and maintain secure, cloud-native infrastructure utilizing AWS, Azure, or GCP. Orchestrate and manage containerized workloads using Docker and Kubernetes. Implement robust Infrastructure as Code (Ia C) using Terraform, Open Tofu, or Cloud Formation. Build, maintain, and optimize secure CI/CD pipelines (Git Hub Actions, Git Lab CI, or Jenkins) for automated software and model deployment.