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

About the role

XtendOps builds AI agents that handle real work for enterprise clients — reading incoming requests, deciding what to do, calling tools across the client's systems, and either acting or preparing work for a human to approve. These agents run against live customer traffic every day.

You will own one or more of them outright: design the flow, build the tools, wire the integrations, ship it, and keep improving it. This is a backend engineering role — we build systems around models; we don't train them.

What you'll do

• 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 that models use correctly.


• 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 — wrong tool, wrong arguments, no tool call, early stop.


• Deploy with Docker to cloud runtimes and instrument runs so they can be debugged after the fact


• Add new features and integrations to live agents without breaking what's already running.


• Explain how an agent works to internal teams and, occasionally, to a client's engineers.

What we're looking for

• 3+ years building production backend software, with strong TypeScript and Node.js


• Hands-on experience building LLM agents that call tools — any framework (Claude Agent SDK, OpenAI, LangChain/LangGraph, Vercel AI SDK, or your own loop)


• Practical experience with MCP or equivalent tool-integration patterns.


• Solid REST API integration experience against third-party systems.


• Comfortable with Docker and at least one cloud platform (AWS, GCP, or Azure)


• Git, testing, and code review as normal working habits.


• Makes decisions and takes initiative. You choose the model, the flow and the tool surface without being told, flag problems nobody has noticed yet, and propose fixes — including to infrastructure you don't own.


• Clear written communication in English.

Nice to have

• Claude Agent SDK or the Anthropic API in production.


• Writing MCP servers, not just consuming them.


• Evaluating LLM output systematically — test sets, regression checks, eval harnesses.


• AWS hands-on: ECS/Fargate, Lambda, IAM, DynamoDB.


• Customer service platforms — Gladly, Zendesk, Salesforce, Amazon Connect.


• Python for data work.

Experience & level

• Mid-level (3–5 yrs): owns features, tools, and integrations inside an agent someone else shaped.


• Senior (6+ yrs): owns the agent and its architecture, and has kept a system running in production before.