[Job-30309] Ai Engineer, Brazil

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.

General Description

We are looking for a Forward Deployed Engineer who uses Generative AI as a foundation of software engineering. This role applies AI across the full Product Development Lifecycle, from requirements and design to deployment and operations. You will design and build AI Agents, apply advanced prompting techniques, and implement architectures like RAG, ReAct, and Chain of Thought. You will also leverage short and long-term memory, MCP, A2A, ACP, and Agentic AI patterns. The ideal candidate uses AI IDEs every day and sees AI not as a tool but as the core of modern engineering.

Responsibilities

Translate product and engineering challenges into AI-driven solutions that enhance speed, quality, and outcomes

Build and deploy AI Agents with advanced reasoning, integrating memory, MCP, custom MCP servers, and A2A

Apply prompt engineering, context engineering, AI steering, RAG, Chain of Thought, ReAct, and other modern AI frameworks to real-world use cases

Partner with product and engineering teams to embed AI, LLMOps, and observability into requirements, coding, testing, monitoring, and operations

Prototype, test, optimise, fine-tune, and scale AI solutions, balancing experimentation with production readiness and inference deployment

Design, run, and automate evals to test LLM outputs for quality, reliability, and safety

Implement security guardrails and robust data integration across agentic workflows to mitigate vulnerabilities

Support pre-sales and client discussions by demonstrating applied AI use cases and outcomes

Stay ahead of research and practice in GenAI and bring them into daily engineering practice

Communicate findings and trade-offs clearly to both technical teams and executives

Required qualifications

Bachelor's Degree in Computer Science, Engineering, Applied Math, or related fields

Strong programming background in Python (or similar) with experience in GenAI frameworks and APIs

Daily use of Generative AI IDEs or environments

Proven experience in Prompt Engineering, Context Engineering, AI Steering, RAG, MCP (Model Context Protocol) and building agent workflows

Solid experience with LLMOps, structured Evals, and LLM observability/tracing tools

Proven knowledge of GenAI Security practices (guardrails, prompt injection mitigation) and secure data integration

Solid understanding of A2A (Agent to Agent) and ACP (Agent Coordination Protocol)

Experience in deploying AI-powered solutions across the product development lifecycle, from design to monitoring

Understanding of how to integrate short and long-term memory in agents

Strong communication skills in English, both technical and business-oriented

Exposure to cloud native environments

Ability to work independently and collaboratively in fast-paced environments

Desired qualifications

Knowledge of reasoning strategies (Chain of Thought, ReAct)

Experience with Agentic AI frameworks, autonomous agents and Multi-Agent Orchestration frameworks (e.g., LangGraph, CrewAI)

Hands-on experience with LLM optimisation, Fine-Tuning techniques, and production inference deployment

Experience developing custom MCP (Model Context Protocol) servers to connect agents with external tools and data

Experience designing and applying evals to validate LLM outputs

Experience with Knowledge Graphs, or hybrid RAG approaches

Experience monitoring AI systems for performance, accuracy, and cost