Senior AI Engineer, Brazil

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.

Requirements:

• 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.