Senior Prompt Engineer

What it does

The Senior Prompt Engineer skill equips AI agents with world-class capabilities in crafting and optimizing prompts for complex AI/ML/Data systems within a production environment. It provides tools and expertise to improve model performance, implement advanced architectures, and ensure scalable, secure, and cost-effective solutions. This skill focuses on applying MLOps and DataOps best practices to prompt engineering workflows.

When to use it

• When needing to optimize the performance of AI models in a production setting.
• For designing and implementing scalable data processing pipelines for large datasets.
• To deploy and monitor machine learning models with high availability and low latency.
• When building agentic systems requiring complex orchestration and evaluation.

Key capabilities

• Advanced prompt engineering patterns and best practices
• Scalable system design and implementation
• Performance optimization at scale for AI/ML workloads
• MLOps and DataOps best practices
• Real-time processing and inference
• Model deployment and monitoring using tools like MLflow and Weights & Biases.
• Utilizes tools including prompt_optimizer.py, rag_evaluator.py, and agent_orchestrator.py.

Example prompts

• "Optimize the prompt for this text classification task to improve accuracy."
• "Evaluate the performance of this Retrieval-Augmented Generation (RAG) system."
• "Deploy this agentic workflow using the provided configuration file."

Tips & gotchas

• This skill requires familiarity with Python and related ML/Data tools.
• The prompt_optimizer.py, rag_evaluator.py, and agent_orchestrator.py scripts are core components, and understanding their usage is essential for effective implementation.
• Refer to the reference documentation (prompt_engineering_patterns.md, llm_evaluation_frameworks.md, agentic_system_design.md) for detailed guidance on patterns, architectures, and best practices.