Data Science & ML Habilidades de Claude

GPT-OSS & vLLM Troubleshooter

Diagnoses and resolves openai_harmony.HarmonyError and tool calling failures when using GPT-OSS models with vLLM.

Python Polars Data Engineering

Accelerates data processing workflows using the Polars DataFrame library for lightning-fast, memory-efficient analysis and pipeline optimization.

FiftyOne Dataset Inference

Automates the creation of FiftyOne datasets from local media files and executes machine learning model inference pipelines.

LLM Evaluation & Benchmarking

Implements comprehensive evaluation frameworks for LLM applications using automated metrics, human feedback, and LLM-as-judge patterns.

Prompt Engineering Patterns

Implements advanced LLM prompt engineering techniques to maximize model performance, reliability, and controllability in production applications.

LangChain Architecture

Builds sophisticated LLM applications using LangChain's agents, memory management, and complex chain patterns.

MLOps Pipeline Workflow

Orchestrates end-to-end machine learning pipelines from data preparation and training to production deployment and monitoring.

RAG Implementation & Vector Search

Builds production-ready Retrieval-Augmented Generation (RAG) systems using vector databases and semantic search to ground AI responses in external data.

LangChain Architecture & Agent Design

Architects sophisticated LLM applications using LangChain with advanced agent patterns, persistent memory, and modular tool integrations.

RAG Implementation Guide

Implements robust Retrieval-Augmented Generation (RAG) systems for LLM applications using vector databases and semantic search.

Prompt Engineering Patterns

Master advanced techniques to maximize LLM performance, reliability, and controllability in production environments.

ML Pipeline Workflow

Orchestrates end-to-end MLOps pipelines from data preparation and training to validation and production deployment.

LLM Application Evaluation

Implement comprehensive evaluation frameworks for LLM applications using automated metrics, human feedback, and benchmarking.

MLOps Pipeline Workflow

Orchestrates end-to-end machine learning lifecycles from data preparation and training to production deployment and monitoring.

LangChain Architecture

Designs and implements sophisticated LLM applications using the LangChain framework with advanced patterns for agents, memory, and tool integration.

Prompt Engineering Patterns

Implements advanced prompt engineering techniques to optimize LLM performance, reliability, and controllability in production environments.

LLM Performance Evaluation

Implements comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and comparative benchmarking.

Vision & Multimodal Capabilities

Powers Claude with advanced visual perception to analyze images, process PDFs, and extract structured data from visual inputs.

RAG Manager

Manages Retrieval-Augmented Generation (RAG) indices to enable semantic search capabilities over BigQuery datasets.

Basilica CLI Helper

Rent high-performance GPUs and manage machine learning training jobs on Basilica's decentralized compute marketplace.

Vector Database Management

Facilitates seamless integration with vector databases for semantic search, retrieval-augmented generation (RAG), and high-dimensional embedding management.

GPU Memory Cleanup

Prevents Jupyter notebook hangs by explicitly managing CuPy GPU memory pools and Python garbage collection.

Local LLM & Home Assistant Integration

Integrates local Large Language Models with Home Assistant and Ollama for private, high-performance smart home automation.

FiftyOne Image Deduplication

Identifies and removes duplicate or visually similar images in FiftyOne datasets using deep learning embeddings.

PocketFlow

Orchestrates complex LLM applications using graph-based abstractions, agentic design patterns, and modular task decomposition.

Senior Prompt Engineer

Optimizes LLM performance through advanced prompt engineering, RAG architecture design, and agentic system orchestration.

RAG Systems Implementation

Builds robust Retrieval-Augmented Generation (RAG) systems for LLM applications using vector databases and semantic search.

Consensus

Consults multiple AI models simultaneously and synthesizes their outputs using configurable strategies to improve accuracy and gather diverse perspectives.

Technical Stock Indicators

Calculates core financial technical indicators including MA, MACD, RSI, and Bollinger Bands for stock market analysis and quantitative trading.

LLM Evaluation & Benchmarking

Implements systematic evaluation strategies for LLM applications using automated metrics, human feedback loops, and benchmarking frameworks.