AI / DevOps Engineer – LLM Applications

About the role

The AI / DevOps Engineer will design, build, and operate AI‑powered software and the supporting infrastructure. The focus is on Large Language Model (LLM) applications, agentic systems, and workflow automation across cloud, on‑premise, private‑cloud, and GPU environments.

Key responsibilities

• Develop AI‑enabled applications that integrate LLM APIs (e.g., Anthropic Claude) and self‑hosted models.
• Build retrieval‑augmented generation (RAG) pipelines using vector databases, embeddings, and semantic search.
• Design and implement agentic systems, tool‑use workflows, and Model Context Protocol (MCP) integrations.
• Create scalable, secure backend services, APIs, and integrations with RESTful APIs, webhooks, and message queues.
• Automate business processes using Power Automate, n8n, Zapier‑style iPaaS, and custom scripts.
• Establish CI/CD pipelines, monitoring, observability, and security controls for production systems.
• Continuously evaluate emerging AI tools, models, and automation techniques.

Required profile

• Strong software development background with experience in AI/ML or DevOps.
• Hands‑on experience deploying and managing GPU‑accelerated workloads.
• Ability to translate business requirements into technical specifications.
• Commitment to continuous learning in a fast‑evolving AI landscape.

Required skills

• LLM APIs (Anthropic Claude or similar)
• Self‑hosted model deployment on GPU infrastructure
• Vector databases, embeddings, semantic search
• Model Context Protocol (MCP)
• RESTful APIs, web services, webhooks, message queues
• Power Automate, n8n, Zapier‑style iPaaS, custom scripting
• CI/CD pipeline creation and management
• Cloud, on‑premise, and private‑cloud deployment
• Observability, monitoring, and secure coding practices