At CI\&T, we help major enterprises transform the potential of AI into real business impact through AI Deployment, AI-native execution, and tech-integrated business solutions. With 30 years of experience in technological transformation, we accelerate innovation with expertise in agentic SDLC, application modernization, Data \& AI, martech, and business strategy. We are 8,000 CI\&Ters across more than 25 countries, collaborating to build solutions with real impact. AI is already part of how we work, evolve, and innovate every day. **Important**: If you reside in the Campinas Metropolitan Region, your physical presence at our city offices is mandatory, per our current attendance policy. You will serve as the architect responsible for defining, designing, and governing the Generative AI agent architecture for voice and chat channels, supporting low-latency, high-accuracy customer service workflows and scalability on GPU infrastructure within Oracle Cloud Infrastructure (OCI). This role focuses on structuring the end-to-end solution architecture, covering agent orchestration, legacy system integration via MCP, security and guardrail layers, observability, traceability, cost monitoring, performance, and LLM response quality. The professional will be responsible for defining architectural standards, guiding engineering teams in implementing orchestrators in Python, supporting technical decisions regarding deployment on OKE, integration with CRM, Billing, and other corporate systems, and ensuring adherence to best practices for security, resilience, governance, and production operations. You will collaborate directly with Engineering, SRE, Security, Data, and Business teams, ensuring Generative AI agents are built with robust, observable, secure, and continuously evolving architecture. Day-to-day responsibilities: * Define the reference architecture for Generative AI agents across voice and chat channels. * Design conversational flows optimized for low latency, scalability, and high availability. * Structure LLM orchestration architecture using frameworks such as LangChain, LlamaIndex, or equivalents. * Define integration standards with corporate systems via MCP Servers, REST APIs, and mTLS. * Guide the use of NeMo Guardrails for security, response control, compliance policies, and risk mitigation. * Define the observability strategy with Langfuse, including traces, cost metrics, latency, quality, and performance. * Support architectural decisions for deployment on OCI, Kubernetes, and OKE. * Design context management, conversational memory, and caching strategies using Redis or equivalent technologies. * Evaluate technical trade-offs among performance, cost, security, accuracy, and user experience. * Ensure architectural alignment across development, SRE, security, data, and business stakeholders. * Review technical designs, support squads during implementation, and ensure adherence to defined standards. * Contribute to architecture evolution based on production metrics, user feedback, and ongoing LLM evaluation. * Required knowledge: * Solution architecture with Generative AI and LLMs. * Cloud-native architecture design on OCI. * Experience with agent orchestration and conversational workflows. * Knowledge of Python applied to AI solutions. * Integration with REST APIs, mTLS, and legacy systems. * Model Context Protocol (MCP) for integration between agents and corporate tools. * GenAI application observability with Langfuse. * Prompt engineering and LLM response evaluation. * Docker, Kubernetes, and architecture for OKE deployment. * Best practices for security, resilience, scalability, and technical governance. Desired knowledge: * NeMo Guardrails. * OCI Generative AI SDK. * Redis for context and conversational memory management. * LangChain, LlamaIndex, or similar frameworks. * Experience with customer service channels, voice, chatbots, or contact centers. * GPU-based solution architecture and low-latency workloads. * LLM evaluation strategies, guardrails, automated testing, and quality monitoring. * Experience in regulated corporate environments, telecom, or large-scale customer service. Keywords: GenAI Architect, AI Architect, Solutions Architect, LLM Architecture, OCI, Langfuse, MCP, NeMo Guardrails, Python, Kubernetes, OKE, Conversational AI, AI Agents. **Our benefits:** * Health and dental insurance; * Meal and food allowance; * Childcare assistance; * Extended parental leave; * Partnerships with gyms and health and wellness professionals via Wellhub (Gympass) TotalPass; * Profit and Results Sharing Program (PLR); * Life insurance; * Continuous learning platform (CI\&T University); * Discount club; * Free online platform dedicated to promoting physical health, mental well-being, and overall wellness; * Pregnancy and responsible parenting course; * Partnerships with online learning platforms; * Language learning platform; * And many more More details about our benefits here: https://ciandt.com/br/pt\-br/carreiras At CI\&T, inclusion begins at first contact. If you are a person with a disability, it is important to **submit your medical report during the selection process.** *Check which information must be included in the report* *by clicking here.* This way, we can ensure the support and accommodations you deserve. **If you do not yet have the qualifying medical report, don’t worry: we can support you in obtaining it.** We have a dedicated Health and Wellness team, inclusion specialists, and affinity groups who will accompany you at every stage. Count on us to walk this journey side by side.
João Silva
Indeed · HR
João Silva
Indeed · HR
