AI Platform Engineer

About the role

You will join the AI Platform team responsible for building and operating the cloud infrastructure, LLM gateway, and serving layer behind Invictus. This is a hands‑on ownership role on Azure where you will take infrastructure from code to production and ensure it runs reliably and cost‑effectively.

Key responsibilities

• Design, implement, and maintain cloud infrastructure for AI workloads on Azure (and other clouds as needed).
• Develop and operate the LLM gateway and serving layer, handling traffic routing, scaling, and performance tuning.
• Manage infrastructure as code using Terraform, Bicep, or comparable tools, including module creation and state management.
• Write production‑grade Python services, leveraging async (asyncio) patterns and concurrency best practices.
• Monitor, debug, and optimise systems using logs, traces, and reproducible testing.
• Apply cost‑optimization strategies across compute, storage, and serverless resources.

Required profile

• 3–5 years of platform, backend, or infrastructure engineering experience with real production ownership.
• Hands‑on experience with a major cloud provider (Azure, AWS, GCP) and solid understanding of compute, networking, containers, and serverless services.
• Proficiency in infrastructure‑as‑code tools such as Terraform or Bicep.
• Strong Python skills, especially with async programming and concurrency concepts.
• Ability to troubleshoot using logs, traces, and systematic reproduction steps.
• Working knowledge of large language model constraints (tokens, context windows, quotas).
• Familiarity with AI‑assisted development tools (e.g., Claude Code, Cursor, Antigravity, OpenCode).

Required skills

• Python
• Asyncio / asynchronous programming
• Terraform or Bicep
• Azure (or AWS/GCP) core services
• Container and serverless compute
• Private networking concepts
• LLM fundamentals (tokens, context windows)
• AI‑assisted development tools