Nice to meet you — we are Evertec! Evertec is a technology company specializing in financial services, with over 27 years of experience and a presence in 26 countries across Latin America and the Caribbean. Processing over 11 billion transactions annually, we are a benchmark in solutions that drive digital transformation across the industry. We offer a comprehensive portfolio of software solutions, serving financial institutions, enterprises, and fintechs seeking innovation, security, and efficiency. Our commitment lies in technological excellence, financial inclusion, and generating sustainable value for customers, employees, and partners — fostering a more connected and accessible ecosystem. Requirements: **Responsibilities** Design and implement production-ready multi-agent architectures Build orchestration systems among specialized agents Develop robust mechanisms for state persistence and context management in long-running sessions Create resilient end-to-end pipelines for ingestion, embedding generation, and contextual retrieval (RAG) Work with hybrid retrieval: vector + structured search Define evaluation strategies, observability practices, and agent tuning methodologies Enhance human-in-the-loop workflows Contribute to evolving AI architecture applied across the SDLC **Mandatory Requirements** Agent Architecture & LLM Engineering Hands-on experience with production multi-agent systems Context Engineering for long-running sessions Advanced Prompt Engineering Orchestration of agents and sub-agents State persistence and contextual memory Human-in-the-loop workflows Agent evaluation and tuning Frameworks / SDKs **Experience with at least one:** Anthropic Claude LangGraph AutoGen CrewAI Semantic Kernel LangChain or equivalents RAG & Contextual Retrieval End-to-end RAG pipeline construction Chunking and embedding strategies Incremental and batch indexing Hybrid search and reranking Recall/precision evaluation Contextual retrieval tuning Vector Databases **Practical experience with at least one:** Pinecone Weaviate Qdrant pgvector Chroma Milvus Cloud & Engineering LLM APIs Advanced Python Distributed integrations Observability and metrics Scalable architecture **Preferred Qualifications** Experience applying RAG to source code Graph databases Service dependency mapping and impact analysis MCPs and contextual integration protocols AI-automated SDLC Large-scale systems Model fine-tuning and evaluation **Profile We Seek** Highly hands-on profile Strong architectural capability Proven experience in production environments Ability to translate AI concepts into scalable platforms Genuine interest in AI Engineering and agentic systems Benefits So, does this resonate with you so far? Then let us tell you what you’ll find here — beyond a dynamic environment: * Meal or food allowance; * Flexible benefit (Flash); * Health insurance; * Partners for psychological, legal, financial, and nutritional support (CLUDE, C4LIFE, and ASQ); * Psicologia Viva; * Dental insurance; * Daycare allowance; * Support for children with special needs; * Fertility assistance; * Extended maternity and paternity leave; * Commuting allowance or remote work allowance (for fully remote contracts); * Gympass (Wellhub) and TotalPass; * Flexible working hours; * Life insurance; * Partner club; * Sesc partnership; * Just dress — no dress code; * Birthday day off; * Beca (education incentive program); * PPR or Bonus — based on goal and result attainment. We value diversity and recognize that what truly adds value is precisely diverse ideas and perspectives. Therefore, race, color, religion, gender and gender identity, nationality, disability, sexual orientation, ancestry, or age will not prevent you from joining our team.
João Silva
Indeed · HR
João Silva
Indeed · HR
