Skip to content
Paula Livingstone writing · projects · tools

Projects

The Frontier Engineer Project

Anthropic is investing $100 million to train 10,000 Frontier Deployed Engineers. This project asks whether an experienced industrial cybersecurity engineer can independently build the same underlying capabilities through targeted study, hands-on engineering and the delivery of a real agentic AI system.

ClaudeClaude CodePythonMCPRAGLLM AgentsLLMOpsCoursera

The Frontier Engineer Project › 05 — LLMOps

MLOps and LLMOps: Deploying and Scaling AI in Production

Moving beyond prototype behaviour into evaluation, testing, observability, deployment and the operational management of LLM systems.

Why this is in the programme

A demonstration can succeed once. An engineering system has to behave well enough, often enough, for its failures to be understood and managed.

That requires considerably more than a capable prompt.

Course

MLOps and LLMOps: Deploying and Scaling AI in Production — Board Infinity

The course covers deployment practices, CI/CD, evaluation, quality gates, observability, tracing and the operational concerns surrounding production LLM systems.

Role in the experiment

This stage provides the bridge between building something interesting and building something defensible.

The project will use these ideas to determine how the eventual system should be tested, monitored and evaluated, including how failures and changes in behaviour can be detected.