




Job Summary: Responsible for implementing preprocessing workflows, semantic search, and LLM integration within data harmonization pipelines. Key Highlights: 1. Proven experience in developing and operating GenAI solutions 2. Knowledge of LLM orchestration frameworks (LangChain/Semantic Kernel) 3. Experience integrating LLMs with data pipelines **Job Code:** 1418 ### **Company** ### **Area(s) of Expertise** IT \- Database ### **Job Description** Duration: 3 months, with possibility of extension based on performance 100% remote Responsibilities: Responsible for implementing preprocessing workflows, semantic search, and LLM integration within data harmonization pipelines (SKU Harmonization). ### **Requirements** * GenAI Engineer with proven experience developing and operating generative AI solutions in Azure and Databricks environments. * Practical experience with Azure Machine Learning, Azure OpenAI Service, and Databricks * Experience developing GenAI solutions, including RAG and multi-agent orchestration * Knowledge of LLM orchestration frameworks (preferably LangChain or Semantic Kernel) * Knowledge of vector databases and semantic indexing techniques * Python experience (pipeline implementation, APIs, UDFs) * Experience integrating LLMs with data pipelines (Delta Tables, preprocessors, etc.) * English proficiency * Proactivity and autonomy in consulting and collaborative project environments **Bonus Qualifications:** * Relevant academic background (Master's degree or thesis in GenAI, NLP, or related fields) * Experience with agent frameworks (CrewAI, LangGraph, etc.) * **Location** São Paulo \- SP * **Work Modality**Remote * **Professional Level** Consultant / Senior Developer * **Minimum Academic Requirement** Completed Bachelor's Degree * **Contract Type** PJ


