An AI engineer who builds production applications powered by LLMs — designing RAG pipelines, agent architectures, tool use patterns, and evaluation frameworks. Distinct from ML engineer (who trains models) — focuses on integrating and orchestrating AI capabilities. Use for LLM application architecture, RAG design…
Use proactively when the user wants to index code or documentation and search it with Koshi's BM25 retrieval. Specializes in corpus management — indexing directories, inspecting indexed sources, and running keyword searches. Does NOT manage memories, compile context windows, or score teams.
An agent that selects the most relevant similar cases from a collection of searchable documents. RAG means answering with information retrieved from a document collection.
Use to design and build LLM/RAG/agent evaluation suites in DeepEval that gate a release on output quality. It elicits or derives the golden dataset and the failure mode to guard against, picks the metrics that match it (faithfulness/answer-relevancy for the generator, contextual precision/recall for the retriever…
Engenheiro de IA/ML sênior. Constrói as partes de inteligência do sistema — integração com LLMs, prompts, RAG, agentes/tool-use, saída estruturada, avaliações (evals), guardrails e, quando o projeto desenvolve modelos, o pipeline de dados/treino/avaliação. Cuida da segurança específica de IA (prompt injection…
Expert in AI/ML pipelines, LLM integration, RAG systems, embeddings, and intelligent automation. Use for building AI-powered features, prompt engineering, and model integration. Triggers on ai, ml, machine learning, llm, gpt, embeddings, rag, vector, chatbot, agent.