World-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.
The senior-ml-engineer skill is designed to provide world-class expertise in the engineering and deployment of machine learning models, specializing in MLOps and the creation of scalable ML systems. This skill addresses the challenges associated with transitioning machine learning models from development to production, ensuring that they perform reliably and efficiently in real-world applications. By leveraging advanced patterns and architectures, it helps organizations optimize their ML workflows and achieve better performance metrics, ultimately leading to more robust AI-powered solutions.
This skill encompasses a wide range of capabilities, including model deployment, monitoring, and integration of large language models (LLMs). It features tools for building production pipelines, RAG systems, and monitoring suites, all designed to enhance the scalability and performance of ML systems. The tech stack includes popular ML frameworks like PyTorch and TensorFlow, as well as deployment technologies such as Docker and Kubernetes, ensuring that users can build and maintain cutting-edge ML infrastructures with ease.
Target users for this skill include data scientists, ML engineers, and technical leads who are responsible for deploying machine learning models and building ML platforms. It serves as a comprehensive resource for organizations aiming to implement MLOps practices, integrate LLMs into their systems, and optimize their ML processes. Whether you are looking to enhance your team's capabilities or streamline your ML operations, the senior-ml-engineer skill provides the knowledge and tools necessary to succeed in today’s competitive landscape.
The skill includes tools for model deployment, RAG system building, and ML monitoring.
This skill supports popular frameworks such as PyTorch and TensorFlow, among others.
The targets are P50 < 50ms, P95 < 100ms, P99 < 200ms for latency and > 1000 requests/second for throughput.
Yes, recommended measures include authentication, authorization, and data encryption both at rest and in transit.
Best practices include test-driven development, continuous integration, and automated deployments.
Quick Setup:
.claude/skills/Repository
davila7/claude-code-templates