AI Adversarial Testing Engineer vs AI Agent Developer

B AI Agent Developer Only

• LLM fundamentals: transformer architecture awareness, tokenization, context windows, temperature/top-p tuning, and model selection trade-offs
• Prompt engineering: system prompt design, few-shot chaining, structured output formatting, and prompt debugging methodology
• Agent architecture patterns: ReAct, Plan-and-Execute, tree-of-thought, reflection loops, and human-in-the-loop designs
• Tool use and function calling: defining tool schemas, handling tool output parsing, error recovery, and multi-tool orchestration
• Retrieval-Augmented Generation (RAG): chunking strategies, embedding models, hybrid search, reranking, and context assembly
• Memory and state management: short-term conversational memory, long-term vector-backed memory, and episodic/procedural memory patterns
• Orchestration frameworks: proficiency in LangChain, LangGraph, CrewAI, AutoGen, or Semantic Kernel for composing agent pipelines
• API design and integration: RESTful and GraphQL API consumption, OAuth flows, webhook handling, and rate-limit-aware request logic