About this role
What You’ll Do
Design, develop, test, deploy, and support high-quality code:
- -
- Building, running, and consuming MCP servers (tool design, auth/OAuth, multi-tenant security, deployment)
-
- Building LLM agents with tool/function calling and multi-agent orchestration (e.g., A2A or similar)
-
- Testing and evaluating agent behaviour, plus observability in production
-
- Contribute to architecture and design discussions, and help evaluate trade-offs around scaling, reliability, and maintainability.
-
- Develop backend services in Python (for AI and Agent work) and Java (for integrating with our client's core platform), with attention to performance and data quality.
-
- Use AI coding tools (e.g., Cursor, Claude Code, GitHub Copilot) as part of your daily workflow to improve productivity and code quality.
-
- Participate in code reviews, giving and receiving feedback that improves the quality and consistency of the codebase.
-
- Identify and flag technical debt, and contribute ideas for how to address it.
-
- Break down development tasks into clear, manageable pieces and execute them reliably.
-
- Collaborate with Product Management and Quality Assurance to refine requirements and ensure your work meets a high bar for quality.
-
- Share what you're learning — whether that's a new pattern, a tool, or a better way of doing something — with the people around you.
-
- Other relevant duties as required.
What We’re Looking For
Must-Have Experience
Be based in Brazil, Colombia, the Dominican Republic, or Mexico.
Strong level of English, written and spoken.
4+ years of backend-heavy software development experience with Java and Python, with extensive usage of Agentic AI.
Solid experience in Java and Python, including working with data structures, relational databases, and SQL.
Hands-on experience with AI coding assistants (such as Cursor, Claude Code, or GitHub Copilot) as part of a daily development workflow.
Familiarity with cloud platforms (especially GCP) and application infrastructure concepts — containers, caching, and distributed systems — is an asset.
Experience working with Microservices
Comfortable working independently on well-defined problems and seeing them through to completion.
Strong attention to detail and a commitment to unit and functional testing.
Experience building AI-driven applications, agentic products and features, working with LLMs, or using frameworks like LangChain or Google ADK:
Hands-on production experience building, running, and consuming MCP servers, including tool design, auth/OAuth, multi-tenant security, and deployment.
Building LLM agents with tool/function calling and multi-agent orchestration (e.g., A2A or similar)
Testing and evaluating agent behaviour, plus observability in production
Computer Science, Engineering, or similar technical aptitude gained through post-secondary education, hands-on experience, or both. Nice-to-haves
Experience with React and TypeScript; familiarity with JavaScript design patterns and single-page apps. Our recruitment process
Recruiter interview (30 min)
Tech interview (30 min)
Client interview - Hiring manager interview (1 hour)
Client interview - Technical interview: design-focused (1h 15min)
Client interview - Technical interview: coding-focused (1 hour)
Client interview - Executive interview (30 min)
We strive to move efficiently from step to step to make the recruitment process as fast as possible.
What we offer
Totally remote, full-time (40h/week)
Work hours - 8 hours a day, East Coast office hours
Independent contractor agreement
Payment in USD, biweekly or monthly - your choice Our team Software Engineering Locations Brazil, Colombia, Dominican Republic, Mexico Remote status Fully Remote Software Engineering ·
Multiple locations
Fully Remote
If you are based in one of the 4 possible countries and have a strong English level, come help our client improve their powerful AI-powered enablement platform, with Python and Agentic AI!
Loading application form