[Job-32047] Mid-Level AI Engineer

Team: Prod_Argo

Location: Brazil

Commitment: Homeoffice

Workplace Type: remote

At CI&T, we help large enterprises transform the potential of AI into real business impact with 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.

What you will do:

• Develop and evolve Generative AI and agentic applications.
• Build RAG-based solutions and enterprise knowledge retrieval components.
• Implement AI agents that interact with tools, APIs, databases, and enterprise systems.
• Work with orchestration patterns such as multi-step workflows, tool use, and Human-in-the-Loop.
• Integrate LLM providers and cloud AI services.
• Design maintainable and testable components following good software engineering practices.
• Implement and maintain evaluation, observability, guardrails, and monitoring capabilities.
• Write automated tests and contribute to CI/CD pipelines.
• Troubleshoot and improve AI applications in production with support from senior team members.
• Collaborate with engineers, architects, product teams, and business stakeholders.

Must-have:

• Strong Python development skills and solid software engineering fundamentals.
• Good understanding of software design principles, including modularity, separation of concerns, testability, maintainability, and clean interfaces.
• Familiarity with common architectural patterns for APIs, services, asynchronous processing, and distributed applications.
• Hands-on knowledge of Generative AI and LLM-based application development.
• Ability to build RAG solutions and/or agentic workflows.
• Familiarity with tool use, function calling, and workflow orchestration patterns.
• Proficiency with at least one AI framework or SDK such as LangGraph, LangChain, Semantic Kernel, LlamaIndex, OpenAI Agents SDK, Strands, or similar.
• Practical knowledge of at least one major LLM provider, such as OpenAI,
• Anthropic Claude, Google Gemini, Azure OpenAI, AWS Bedrock, or similar.
• Good understanding of embeddings, vector search, and knowledge retrieval concepts.
• Familiarity with AI evaluation, observability, guardrails, and production monitoring.
• Ability to integrate AI applications with APIs, databases, and cloud services.
• Working knowledge of Docker, CI/CD, automated testing, and version control.
• English proficiency for daily collaboration with international teams.

Nice-to-have:

• Exposure to multi-agent or long-running agent workflows.
• Knowledge of Agentic SDLC or developer tooling integrations.
• Familiarity with knowledge graphs or GraphRAG.
• Hands-on knowledge of Datadog LLM Observability, LangSmith, OpenTelemetry, or similar platforms.