Software Engineer – Applied AI

This is a fully remote position, open to applicants in Brazil.

📋 Description

• Engage actively throughout the complete lifecycle of AI products, ranging from prototyping new initiatives to deploying and maintaining production AI services for both internal teams and external clients.

• Strategize, execute, and uphold end-to-end agents, which involves selecting appropriate models, crafting prompts, establishing Model Context Protocols (MCPs) and tool integrations, conducting evaluations, and ensuring production stability.

• Utilize AI technology daily by leveraging AI agents (e.g., Claude Code, Cursor, Codex, custom pipelines) to plan, implement, review, and troubleshoot your tasks.

• Contribute to the foundational platform utilized by other Belvo squads for AI deployment, concentrating on agent abstractions, conversation and state storage, durable workflow orchestration, streaming interfaces, observability, and guardrails.

• Remain at the cutting edge of the industry by experimenting with new models, agentic frameworks, and MCP-native patterns, making selections based on practical production reliability, cost, and latency considerations.

• Implement and monitor AI pipelines using Langfuse and Datadog to troubleshoot failed agent executions, identify regressions, and maintain production health.

• Assist in enablement initiatives that aid other Belvo squads in safely adopting AI through reference implementations, integration patterns, and shared tools.

⛳️ Requirements

• Over 5 years of experience in software engineering or developing technical products.

• Proven contribution to the development and maintenance of LLM-powered systems (agentic systems) within production environments.

• Comfortable working with agentic frameworks (e.g., Pydantic AI, LangGraph, Claude Agent SDK, AI SDK) and applying them effectively in context.

• Familiar with the Model Context Protocol (MCP) and its fundamental design principles.

• Regularly utilize coding agents (e.g., Claude Code, Cursor, Codex, GitHub Copilot) in your daily workflow and continually seek ways to enhance your output with them.

• Proficient in interpreting agent traces, debugging AI pipelines, and utilizing AI observability tools (e.g., Langfuse, Datadog).

• Strong engineering expertise in Python (preferably with FastAPI or Django) with an emphasis on writing maintainable, well-tested code.

• Experience with cloud infrastructure (ideally AWS) and infrastructure-as-code (e.g., Terraform), and comfortable deploying and maintaining your own services.

• Inquisitive about new models and tools, yet practical regarding what is suitable for production use.

• Value early progress sharing, close collaboration with stakeholders, and view learning as an iterative journey.

• Thrive in fast-paced or small-team environments where ownership, collaboration, and adaptability are essential.

• Proficient in both written and spoken English.

🏝️ Benefits

• Stock options (we are all owners and this is very important to us)

• Annual company bonus linked to company performance

• Flexible working hours

• Remote friendly

• Pet friendly

• Health Insurance

• Paid time off on your birthday

• Renew your laptop every 3 years

• Training Budget

• Team building events

• Bank holidays swap within 30 days

• Fitness/ wellness stipends

• Yearly company offsite

• Fresh fruit every week, all-you-can-drink tea and coffee

• Extra days off when completing company anniversary

• Yearly department offsite

• Company Offsite