Does this skill support Large Language Models (LLMs)?

Yes, it includes specialized patterns for LLM integration, fine-tuning, RAG system architecture, and agentic AI development using frameworks like LangChain and LlamaIndex.

Can it help with cloud-native ML deployment?

Absolutely. It covers deployment best practices for AWS, GCP, and Azure using Docker, Kubernetes, and infrastructure-as-code patterns.

What performance targets does this skill aim for?

It is designed to help engineers achieve P99 latency under 200ms and support throughput exceeding 1000 requests per second.

Which machine learning frameworks are supported?

The skill provides expert-level guidance for PyTorch, TensorFlow, Scikit-learn, XGBoost, and distributed tools like Spark and Databricks.

What does the Senior ML Engineer skill help with?

It assists in moving ML models from research to production, focusing on MLOps, scalability, performance optimization, and engineering excellence.

Senior ML Engineer

Name: Senior ML Engineer
Author: BbgnsurfTech

byBbgnsurfTech

•

数据科学与机器学习

Productionizes machine learning models and builds scalable MLOps systems with world-class engineering standards.

关于

The Senior ML Engineer skill empowers Claude to act as a world-class architect for production-grade AI and data systems. It provides deep expertise in MLOps patterns, scalable system design, and performance optimization for high-throughput inference. Whether you are transitioning research notebooks to Kubernetes, building enterprise-scale RAG systems, or implementing automated model monitoring and drift detection, this skill provides the patterns, scripts, and best practices necessary for robust, secure, and cost-optimized machine learning infrastructure.

主要功能

Production-grade MLOps and DataOps pipeline implementation
Scalable RAG system architecture and LLM integration patterns
High-performance inference optimization (P99 < 200ms)
3 GitHub stars
Distributed data processing with Spark, Airflow, and Kafka
Comprehensive model monitoring, observability, and security audits

使用场景

Building and deploying automated retraining pipelines for production models
Architecting high-availability RAG systems for enterprise data retrieval
Implementing model monitoring suites to detect data drift and performance decay

关于

主要功能

Production-grade MLOps and DataOps pipeline implementation
Scalable RAG system architecture and LLM integration patterns
High-performance inference optimization (P99 < 200ms)
3 GitHub stars
Distributed data processing with Spark, Airflow, and Kafka
Comprehensive model monitoring, observability, and security audits

使用场景

Building and deploying automated retraining pipelines for production models
Architecting high-availability RAG systems for enterprise data retrieval
Implementing model monitoring suites to detect data drift and performance decay