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
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
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.
Master MLOps fundamentals - lifecycle, principles, tools, practices, and organizational adoption
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
Cost optimization for AI workloads - model selection, GPU sizing, commitment strategies, and multi-cloud cost management
PyTorch, TensorFlow, neural networks, CNNs, transformers, and deep learning for production
Deep learning foundations including neural network basics, backpropagation, optimization, regularization, and training best practices.
Performs rigorous time series cross-validation using expanding and sliding windows. Use when needing to evaluate the performance of time series models on unseen data. Trigger with cross validate time series, evaluate forecasting model, time series backtesting.
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.
Build computer vision solutions - image classification, object detection, and transfer learning
Efficient AI techniques including model compression, quantization, pruning, knowledge distillation, and hardware-aware optimization for production systems.
Modify cognitive parameters and behavioral settings.
Analyze GRPO training runs for learning dynamics and pipeline performance. Use when diagnosing training issues, reviewing Elo progression, checking throughput, or updating experiment results.
Performs rigorous time series cross-validation using expanding and sliding windows. Use when needing to evaluate the performance of time series models on unseen data. Trigger with "cross validate time series", "evaluate forecasting model", "time series backtesting".
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Defensive techniques using adversarial examples to improve model robustness and security
Feature engineering techniques including feature extraction, transformation, selection, and feature store management for ML systems.
