Senior Backend AI Agent Engineer

Hammerjack Pty Ltd; Philippines; On-site; PHP 1,339,000 - 2,009,000; Full time

Job summary

Hammerjack Pty Ltd seeks a backend engineer to own one or more AI agent projects end-to-end, from design to production. You will build tooling, wire integrations, and ship agents that operate against live customer traffic, focusing on backend systems around models rather than training them.

You will design MCP-backed tools, deploy with Docker to cloud runtimes, and iterate agent instructions while debugging production issues and expanding capabilities for clients.

Qualifications

• 3+ years building production backend software.
• Strong TypeScript and Node.js experience.
• Hands-on experience building LLM agents that call tools.
• REST API integration experience with third-party systems.
• Comfortable with Docker and at least one cloud platform (AWS, GCP, or Azure).

Responsibilities

• Build and ship AI agents end to end, from design through production.
• Design and implement the tools and MCP servers agents call, including schemas and descriptions.
• Integrate third-party APIs and internal services behind those tools—auth, retries, rate limits, idempotency.
• Write and iterate the agent instructions that drive behaviour.
• Configure the agent loop: model selection, turn limits, reasoning effort, tool permissions.
• Debug agent behaviour in production and fix issues with tools or arguments.
• Deploy with Docker to cloud runtimes and instrument runs for post-mortem debugging.
• Add new features and integrations to live agents without breaking existing ones.
• Explain how an agent works to internal teams and sometimes to a client's engineers.

Skills

TypeScript

Node.js

REST APIs

Docker

Cloud platforms

Git & Testing

English communication

Tools

Claude Agent SDK

OpenAI API

LangChain/LangGraph

Vercel AI SDK

MCP servers

Job description

Hammerjack Pty Ltd seeks a backend engineer to own one or more AI agent projects end-to-end, from design to production. You will build tooling, wire integrations, and ship agents that operate against live customer traffic, focusing on backend systems around models rather than training them.

You will design MCP-backed tools, deploy with Docker to cloud runtimes, and iterate agent instructions while debugging production issues and expanding capabilities for clients.