Forward Deployed Engineer - LATAM

What You'll Do7

• Map the client's technology stack and spot tools staff built without engineering support.
• Take over unfamiliar codebases, stabilize them, and shift them to a better architecture while preserving behavior users depend on. Use parity tests to prove accuracy where it matters.
• Ship retrieval systems, multi-step agents, and custom AI tools that connect to the client's current systems.
• Compare deployment options against the client's environment, budget, and skill set. Explain tradeoffs in plain terms and recommend a platform even when it differs from the client's first choice.
• Build reusable integration services with service accounts, per-solution keys, and secret management, and guide the work through security review.
• Investigate why end users avoid a tool, fix the cause, and set up feedback loops that track usage and time saved.
• Document decisions, pair with client staff, and remove single points of failure so the capability remains after the engagement ends.

Requirements9

• Production software delivery experience, including work with customers or business stakeholders.
• Strong Python or TypeScript skills, with enough comfort to work in the other language.
• Hands-on LLM API work: prompting, retrieval, tool use, and multi-step or multi-agent workflows, plus a clear view of where those systems fail.
• Backend fundamentals across relational databases such as PostgreSQL, API design, authentication, and deployment pipelines.
• A track record of inheriting code you did not write and improving it without breaking user-facing behavior.
• Security judgment for AI systems: secrets handling, data classification, least-privilege access, and work with information security teams.
• Ability to explain a technical tradeoff to an executive in a few sentences and to tell a client when their preferred option is wrong, with tact.
• Comfort with ambiguity, including resetting scope when a project changes.
• Time management across more than one project.

Preferred Qualifications6

• Microsoft ecosystem experience with Copilot, Copilot Studio, Azure AI Foundry, and Word or PowerPoint document generation.
• Firebase (Firestore, Cloud Functions) or Supabase-style Postgres platforms with row-level security.
• React and Next.js front-end work, plus consulting or independent client work.
• Workflow orchestration tools such as n8n.
• Model Context Protocol (MCP) server implementation and gateway design that exposes data to non-engineers.
• Familiarity with AI governance frameworks such as the NIST AI Risk Management Framework.

Who Should Apply

The ideal candidate has shipped production software with customers, moved between Python and TypeScript, and taken over code someone else wrote. You can scope an LLM application, explain tradeoffs to executives, and keep security and adoption in view from the first client meeting.

Salary Insight