AI Engineer

Signify Technology; Brasil; Remote; BRL 180,000 - 300,000; Full time

Job summary

Casado is seeking an AI Engineer to design, build, and improve AI agents for real product use cases. The role involves developing agent workflows, evaluation frameworks, and observability to ensure reliable production deployments.

The candidate will work with LangGraph, Langfuse, and OpenRouter in a remote Brazil-based contractor arrangement, collaborating with a distributed team and cross-functional partners to advance AI capabilities in the fintech product.

Qualifications

• Strong software engineering skills with end-to-end delivery experience.
• Practical experience evaluating AI systems and improving reliability.
• Understanding of challenges in deploying LLMs to production.
• Clear communication and experience working with distributed teams.

Responsibilities

• Design, build and improve AI agents for real product use cases.
• Develop agent workflows and the supporting systems they need to operate reliably.
• Build evaluation frameworks to measure quality and identify failures.
• Improve observability so the team can understand agent behavior and performance.
• Work with multimodal models and integrations where needed.
• Collaborate with product and engineering colleagues across a distributed team.

Skills

Software engineering

AI systems evaluation

LLMs in production

Distributed teamwork

Tools

LangGraph

Langfuse

OpenRouter

Job description

AI Engineer — Agentic AI

Location: Remote, Brazil

Engagement: Long-term contractor - hire

The opportunityI’m working with a growing US fintech company that is looking for an AI Engineer based in Brazil. The business builds technology that helps companies offer financing to their customers, and it is expanding the AI capabilities within its product.

This is a hands-on role for someone who has built AI agents and understands how to make them reliable in production.

What you’ll doDesign, build and improve AI agents for real product use cases.

• Develop agent workflows and the supporting systems they need to operate reliably.
• Build evaluation frameworks to measure quality and identify failures.
• Improve observability so the team can understand agent behaviour and performance.
• Work with multimodal models and integrations where needed.
• Collaborate with product and engineering colleagues across a distributed team.

What we’re looking forExperience building and shipping AI agents beyond proof of concept.

• Strong software engineering skills, with the ability to take work from design through delivery.
• Practical experience evaluating AI systems and improving their reliability.
• An understanding of the challenges of using LLMs in production.
• Clear communication and experience working with distributed teams.

The team uses LangGraph, Langfuse and OpenRouter. Experience with these tools would be useful, but relevant experience with other agent frameworks, evaluation tools and model providers is welcome.

Working arrangement

This is a remote role for someone based in Brazil, working directly with the company under a contractor arrangement. The full compensation and benefits package will be discussed during the process.