aws-ai-services-expert
Build AI applications on AWS using Bedrock, SageMaker, and AI/ML services with best practices for enterprise deployment
Найдите подходящую возможность для вашего агента.
Build AI applications on AWS using Bedrock, SageMaker, and AI/ML services with best practices for enterprise deployment
Claude Code SDK integration for building AI-powered applications with OAuth and API Key authentication
Delegate user perspective reviews to GPT-5.2 Reviewer agent. Use when (1) Feature implementation is complete and needs UX validation, (2) User asks to create a pull request (review before PR), (3) User explicitly requests review ("review this", "check this", "user perspective"), (4) UX concerns need evaluation (user experience, usability, edge cases), (5) Documentation clarity needs checking from user perspective. DO NOT use for writing tests (use test-writer), quick file searches (use quick-helper), code implementation (Main Claude), or performance analysis.
Answers questions about Claude Code features, configuration, and usage from local documentation synced from code.claude.com. Use when users ask about hooks, plugins, skills, MCP servers, slash commands, sub-agents, settings, permissions, sandboxing, CLAUDE.md memory files, model selection, costs, IDE integrations (VS Code, JetBrains), CI/CD (GitHub Actions, GitLab), or cloud providers (Bedrock, Vertex, Azure).
Performs dynamic, reflective problem-solving through iterative thought chains. Use for complex planning requiring revision, branching, backtracking, or hypothesis verification. Ideal for multi-step analysis where context maintenance is required or the full scope isn't initially clear.
Model optimization techniques including hyperparameter tuning, architecture search, training optimization, and performance profiling for ML systems.
Real-time monitoring and detection of adversarial attacks and model drift in production
Extract, learn, and integrate PR feedback into the Violet brain
Track ML experiments with proper logging and reproducibility. Use when training models or running experiments.
Test AI training pipelines for data poisoning vulnerabilities and backdoor injection
Build and train neural networks with PyTorch - MLPs, CNNs, and training best practices
ML framework best practices for PyTorch, TensorFlow, scikit-learn, and modern ML libraries including training patterns and optimization.
Implement native Rust ML inference with Candle framework. Use when building GPU-accelerated ML pipelines without Python dependencies.
Optimizes AI models for edge deployment through quantization, lazy loading, and memory management. Use when deploying models to resource-constrained environments, mobile devices, or edge computing scenarios. Do not use for cloud deployment, model training, or data preprocessing.
Model development practices including model selection, training pipelines, hyperparameter tuning, evaluation, and model selection strategies.
Cost optimization for AI workloads - model selection, GPU sizing, commitment strategies, and multi-cloud cost management
Design, configure, launch, and analyze ablation sweeps for GRPO training. Use for hypothesis testing, hyperparameter experiments, and systematic comparisons.
Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.