senior-ml-engineer
NewWorld-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.
Summary
This skill equips you with expert-level guidance for productionizing machine learning models, from building scalable ML pipelines and MLOps infrastructure to deploying LLMs and agentic systems.
- It covers the full lifecycle—feature stores, model monitoring, fine-tuning, and RAG—helping you avoid common pitfalls and ship robust ML systems faster.
Install & Usage
~/.claude.jsonAdd the configuration to "mcpServers": { "senior-ml-engineer": { "command": "...", "args": [] } }
/mcpUse Cases
Usage Examples
/senior-ml-engineer Design a PyTorch training pipeline for a transformer model with distributed data parallelism and mixed precision.
/senior-ml-engineer Help me set up MLflow for experiment tracking and model registry, then deploy the best model to a Kubernetes cluster.
I need to build a RAG system for customer support. Guide me through chunking, embedding, vector DB setup, and LLM integration with monitoring.
Security Audits
Frequently Asked Questions
What is senior-ml-engineer?
This skill equips you with expert-level guidance for productionizing machine learning models, from building scalable ML pipelines and MLOps infrastructure to deploying LLMs and agentic systems. It covers the full lifecycle—feature stores, model monitoring, fine-tuning, and RAG—helping you avoid common pitfalls and ship robust ML systems faster.
How to install senior-ml-engineer?
To install senior-ml-engineer: open your mcp config (~/.claude.json), then add the config to "mcpServers": { "senior-ml-engineer": { "command": "...", "args": [] } }. Finally, /mcp in Claude Code.
What is senior-ml-engineer best for?
senior-ml-engineer is a mcp categorized under General. It is designed for: deployment, agent, ai-&-ml, devops. Created by davila7.
What can I use senior-ml-engineer for?
senior-ml-engineer is useful for: Design and implement a production-grade ML training pipeline with distributed PyTorch or TensorFlow.; Set up a feature store and online serving layer for real-time model inference.; Deploy a fine-tuned LLM with a RAG system using vector databases and agentic orchestration.; Implement model monitoring, drift detection, and automated retraining for a deployed ML service.; Architect a multi-model serving infrastructure with A/B testing and canary deployments.; Integrate an agentic AI system that uses tool calling and memory for complex multi-step tasks..