[Job- 32285] Senior AI Engineer, Brazil
At a glance
Senior AI Engineering role at CI&T. Remote, Brazil.
Pay not stated AI Engineer salary
aimlroles summary, based on the employer's posting.
What you'll do
- Build and maintain Python-based AI agents and LLM applications on AWS
- Shape prompts and agent workflows, then assess accuracy, reliability and consistency with evaluation frameworks
- Set baselines and automated checks to catch regressions in agent behavior
- Add safeguards and validation, and investigate hallucinations or inconsistent responses
- Connect LLM features to backend APIs, document processing and cloud systems while tracking production behavior
What you bring
- Professional background in AI or machine learning engineering, or software development involving production AI applications
- Strong Python skills, including API development, integrations and automated testing
- Practical experience with LLM applications and agent workflows, including prompting and orchestration
- Experience testing LLM outputs and measuring quality, plus familiarity with AWS services such as Bedrock or Lambda
- Advanced or fluent written and spoken English for remote collaboration
Who this fits
This role suits a senior AI engineer who can improve agent behavior and deliver production-ready features with engineering and product teams. The position is remote in Brazil, and advanced or fluent English is essential.
From the employer
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.
We are looking for an experienced AI Engineer to join our nearshore team working on an AI-powered media planning platform. In this role, you will focus on developing, evaluating, and improving intelligent AI agents powered by Large Language Models (LLMs). You will work with AWS Bedrock and modern AI technologies to build reliable agentic workflows, optimize agent behavior, implement evaluation frameworks, and ensure AI-generated outputs are accurate, secure, and consistent. Your work will directly impact the quality, reliability, and scalability of production AI solutions.
Responsibilities:- Design, develop, and maintain AI agents and LLM-powered applications using Python and AWS services.
Implement and optimize prompt engineering, agent orchestration, and intelligent decision-making workflows. - Develop evaluation frameworks to measure agent accuracy, reliability, and behavioral consistency.
- Establish performance baselines, automated tests, and regression validation for changes to agent behavior.
- Implement guardrails and validation mechanisms to ensure safe and reliable AI-generated outputs.
- Develop intelligent information retrieval, filtering, ranking, and selection strategies using LLMs.
- Investigate and resolve issues related to hallucinations, incorrect interpretations, and inconsistent agent responses.
- Build end-to-end AI features integrating LLMs with backend APIs, document processing, and cloud infrastructure.
- Improve agent observability through execution tracing, session tracking, and production monitoring.
- Collaborate with engineering and product teams to deliver scalable, production-ready AI solutions.
- Optimize LLM performance, latency, and operational costs through experimentation and measurable improvements.
- Solid professional experience in AI engineering, machine learning engineering, or software development with production AI applications.
- Strong proficiency in Python and experience developing APIs, integrations, and automated tests.
- Hands-on experience building applications using Large Language Models (LLMs) and agentic AI workflows.
- Experience with prompt engineering, LLM orchestration, and structured output generation.
- Experience evaluating LLM outputs, implementing testing strategies, and measuring AI application quality.
- Understanding of LLM limitations, including hallucinations, response variability, and reliability challenges.
- Experience with AWS services (Bedrock, Lambda, S3, CloudWatch, or similar).
- Strong knowledge of software engineering best practices, CI/CD, and cloud-based application development.
- Strong analytical and problem-solving skills with the ability to troubleshoot complex agent behavior.
- Advanced or fluent English communication skills (both written and verbal) are essential for collaboration in a remote environment.