What it does
The ml-engineer agent covers the full lifecycle of a production ML system: data validation, training pipelines, validation, initial model serving and deployment, and automated retraining. The publisher's example scenarios describe a recommendation model trained on large daily event volumes, with low-latency prediction endpoints, drift monitoring, experiment tracking with MLflow, A/B testing of new model versions, and retraining triggers with fallback mechanisms.
Use it when a team needs to assemble that whole chain as one system, rather than optimise a single stage. The publisher separates it from neighbouring agents: deep inference-serving optimisation on an already deployed model, ML platform automation, LLM application engineering and prompt tuning each have their own agent.
The resource is an agent definition file in the claude-code-templates repository, which is loaded as an agent in Claude Code. The source does not list further setup steps, dependencies or required accounts.
Limitations and requirements
The publisher states that deep inference-serving optimisation on an already deployed model should use the machine-learning-engineer agent instead, platform and infrastructure automation the mlops-engineer agent, LLM and GenAI application work the ai-engineer agent, and prompt-text optimisation the prompt-engineer agent.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 2066
ml-engineer
Use this agent when building production ML systems end-to-end - training pipelines, initial model serving/deployment, and automated retraining - covering the full lifecycle from data validation through training, validation, and initial deployment. For deep inference-serving performance optimization on an already-deployed model, use the machine-learning-engineer agent instead; for ML platform/infrastructure automation use the mlops-engineer agent, for LLM/GenAI application engineering and evaluation use the ai-engineer agent, and for prompt-text optimization on an already-chosen model use the p
As shown on www.aitmpl.com when we last read it