AI Agent Engineer: Build Proactive, Self-Hosting Agents

SERVICECO PTE. LTD.; Metro Manila; On-site; PHP 1,339,000 - 2,009,000; Full time

Job summary

SERVICECO PTE. LTD. seeks an experienced AI platform engineer to build and run an agent platform on OpenClaw or a similar self-hosted runtime on AWS. You will craft agents with multiple tasks, ensure memory/context/goals, and handover to humans efficiently.

You will tune LLMs, manage tools and implement MCP servers connecting to emails and collaboration tools, while keeping security and costs in check. Strong coding in Python/TypeScript is essential.

Qualifications

• Hands-on OpenClaw or similar agent runtime experience.
• Proactive agents, not just reactive chatbots.
• Deep knowledge of LLMs: prompting, tool calling, RAG, model selection, cost and latency trade-offs.
• Experience running open-weight models (Ollama, vLLM) and knowing when fine-tuning is worth it.
• Built custom MCP servers yourself, from scratch.
• Strong Python or TypeScript and real AWS experience.

Responsibilities

• Build and run our agent platform on OpenClaw (or a similar self-hosted runtime) on AWS.
• Build agents with multiple jobs and tasks, managed by one lead agent.
• Set agents up properly from the start: memory, context, goals and clear handover to humans.
• Choose, set up and tune LLMs, both off the shelf (Claude, GPT, Gemini) and open-weight or customised models.
• Build fully custom MCP servers that connect agents to email, Slack, project tools and business systems.
• Keep it secure, reliable and cheap to run: secrets, permissions, logging, cost limits.
• Test agents properly before and after every change.

Skills

OpenClaw

Python

TypeScript

AWS

LLMs

Prompting

RAG

Automation

Tools

OpenClaw setup

Ollama

vLLM

APIs

Job description

SERVICECO PTE. LTD. seeks an experienced AI platform engineer to build and run an agent platform on OpenClaw or a similar self-hosted runtime on AWS. You will craft agents with multiple tasks, ensure memory/context/goals, and handover to humans efficiently.

You will tune LLMs, manage tools and implement MCP servers connecting to emails and collaboration tools, while keeping security and costs in check. Strong coding in Python/TypeScript is essential.