Senior DevOps Engineer

Role Overview: As a Senior DevOps Engineer at BrezQ, you will be responsible for designing, automating, and securing the infrastructure for custom software solutions and AI integrations, specifically focusing on Generative AI and LLMOps pipelines. Your role will involve setting up scalable cloud environments, building CI/CD pipelines, and establishing deployment frameworks for Large Language Models (LLMs) and foundational AI applications. Key Responsibilities: - Design and manage cloud infrastructure tailored for hosting, fine-tuning, and serving Generative AI models. - Implement and manage infrastructure for AI orchestration frameworks such as LangChain, LlamaIndex, and Semantic Kernel. - Optimize vector databases for efficient Retrieval-Augmented Generation (RAG) pipelines. - Implement cost-optimization strategies for heavy compute resources like GPUs/TPUs. - Architect, scale, and maintain secure, cloud-native infrastructure using AWS, Azure, or GCP. - Orchestrate and manage containerized workloads using Docker and Kubernetes. - Implement Infrastructure as Code (IaC) using Terraform, OpenTofu, or CloudFormation. - Build, maintain, and optimize secure CI/CD pipelines for automated software and model deployment. - Set up advanced observability tools to track infrastructure health and AI model performance metrics. - Collaborate with engineering teams to ensure highly secured IT solutions, embedding data privacy and vulnerability scanning. Qualifications Required: - 5+ years of total experience in DevOps/Cloud Engineering, with at least 1-2 years actively supporting AI/ML or GenAI workloads in production. - Practical exposure to deploying LLMs and familiarity with AI ecosystems. - Deep expertise in Kubernetes and Docker. - Proven mastery of Terraform for Infrastructure as Code. - Familiarity with traditional databases and vector stores. - Strong scripting and automation skills in Python, Go (Golang), or Bash. Role Overview: As a Senior DevOps Engineer at BrezQ, you will be responsible for designing, automating, and securing the infrastructure for custom software solutions and AI integrations, specifically focusing on Generative AI and LLMOps pipelines. Your role will involve setting up scalable cloud environments, building CI/CD pipelines, and establishing deployment frameworks for Large Language Models (LLMs) and foundational AI applications. Key Responsibilities: - Design and manage cloud infrastructure tailored for hosting, fine-tuning, and serving Generative AI models. - Implement and manage infrastructure for AI orchestration frameworks such as LangChain, LlamaIndex, and Semantic Kernel. - Optimize vector databases for efficient Retrieval-Augmented Generation (RAG) pipelines. - Implement cost-optimization strategies for heavy compute resources like GPUs/TPUs. - Architect, scale, and maintain secure, cloud-native infrastructure using AWS, Azure, or GCP. - Orchestrate and manage containerized workloads using Docker and Kubernetes. - Implement Infrastructure as Code (IaC) using Terraform, OpenTofu, or CloudFormation. - Build, maintain, and optimize secure CI/CD pipelines for automated software and model deployment. - Set up advanced observability tools to track infrastructure health and AI model performance metrics. - Collaborate with engineering teams to ensure highly secured IT solutions, embedding data privacy and vulnerability scanning. Qualifications Required: - 5+ years of total experience in DevOps/Cloud Engineering, with at least 1-2 years actively supporting AI/ML or GenAI workloads in production. - Practical exposure to deploying LLMs and familiarity with AI ecosystems. - Deep expertise in Kubernetes and Docker. - Proven mastery of Terraform for Infrastructure as Code. - Familiarity with traditional databases and vector stores. - Strong scripting and automation skills in Python, Go (Golang), or Bash.