proagent-ml-ai

Overview of all ML & AI capabilities: model training, feature engineering, experiment tracking, deployment, LLM applications, and MLOps.

Review ML artifacts: model architecture, training pipeline, inference optimization, and data quality.

Execute ML/AI operations: train-model, build-pipeline, setup-experiment, create-embedding, deploy-model, build-knowledge-graph, create-meta-prompt, evaluate-with-judge, or validate-pipeline.

Senior ML/AI engineer specializing in model training (scikit-learn, TensorFlow, PyTorch, XGBoost), feature engineering, hyperparameter optimization, experiment tracking (MLflow, W&B), model deployment (FastAPI, SageMaker, Bedrock, Vertex AI), MLOps pipelines, LLM application development, RAG systems, embeddings, vector stores, prompt engineering, knowledge graph integration (Graphiti), meta-prompting frameworks, LLM judge evaluation, ML pipeline validation workflows, and production model monitoring. Use for any machine learning, deep learning, or AI engineering task.

Building ML & AI Systems - model training, inference optimization, MLOps pipelines, experiment tracking, prompt engineering, embeddings, vector stores, LLM application development, RAG systems, knowledge graph integration (Graphiti), meta-prompting frameworks, LLM judge evaluation, and AWS AI services (SageMaker, Bedrock). Use when performing any machine learning, deep learning, or AI engineering task.

4 hooks across 2 events