Ingeniero/a Senior de IA

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:

- Own AI solutions from technical discovery through production and continuous improvement.
- Design and evolve Generative AI, RAG, and agentic applications.
- Define technical approaches considering quality, scalability, security, cost, maintainability, and operational impact.
- Design agents and workflows that interact with tools, APIs, databases, messaging systems, and enterprise platforms.
- Define orchestration patterns such as Human-in-the-Loop, long-running workflows, retries, fallback strategies, and deterministic controls.
- Establish evaluation, observability, guardrails, and reliability practices for AI applications.
- Guide model, retrieval, framework, and infrastructure choices based on technical trade-offs.
- Troubleshoot complex production issues involving models, prompts, retrieval, tools, integrations, and infrastructure.
- Collaborate with architects, engineers, product teams, and business stakeholders, providing technical guidance when needed.
- Support other engineers and contribute to engineering standards and best practices for AI solutions.

Must-have:

- Strong Python development skills and solid software engineering foundations.
- Proven ability to design and deliver production-grade Generative AI and LLM-based solutions.
- Deep knowledge of software design principles, including modularity, separation of concerns, testability, maintainability, resiliency, and clean interfaces.
- Ability to design services, APIs, asynchronous workflows, and distributed components for production environments.
- Hands-on knowledge of RAG and agentic AI patterns, including tool use, function calling, orchestration, Human-in-the-Loop, and guardrails.
- Strong understanding of embeddings, vector search, retrieval strategies, chunking, reranking, and enterprise knowledge retrieval.
- Proficiency with AI frameworks or SDKs such as LangGraph, LangChain, Semantic Kernel, LlamaIndex, OpenAI Agents SDK, Strands, or similar.
- Practical knowledge of multiple LLM providers such as OpenAI, Anthropic Claude, Google Gemini, Azure OpenAI, AWS Bedrock, or similar.
- Ability to assess trade-offs between models, providers, orchestration approaches, retrieval strategies, and infrastructure options.
- Strong knowledge of AI evaluation and observability, including quality, tracing, latency, token usage, failures, and cost.
- Good understanding of cloud-native practices such as scalability, resiliency, secrets management, configuration management, observability, and access control.
- Strong working knowledge of Docker, CI/CD, automated testing, and version control.
- Fluent English for technical discussions with international stakeholders.

Nice-to-have:

- Knowledge of multi-agent systems and long-running agent workflows.
- Background in Agentic SDLC, coding agents, GitHub, or developer tooling integrations.
- Familiarity with knowledge graphs, GraphRAG, or hybrid retrieval architectures.
- Hands-on knowledge of Datadog LLM Observability, LangSmith, OpenTelemetry, or similar platforms.