AI Engineer (AI Agents & Automation)

Helius Technologies; Singapore; On-site; SGD 180,000 - 240,000; Full time

Benefits offered by this job

Restaurant d'entreprise

Indemnités de stage/alternance

Job summary

Helius Technologies Pte Ltd in Singapore invites an hands-on AI Engineer to design, build, and deploy enterprise Generative AI applications, autonomous agents, and intelligent workflow automations. You will combine agentic frameworks with low-code orchestration using n8n, build high‑performance Retrieval‑Augmented Generation systems, and leverage Claude Code to accelerate AI adoption.

Collaborate with infra and engineering teams to prototype, deploy, and scale enterprise AI solutions in Linux

Qualifications

• Hands-on experience with Generative AI tooling and agent frameworks.
• Experience building autonomous agents with memory and RAG pipelines.
• Proficient in Python and familiar with REST APIs and security basics.

Responsibilities

• AI Agent & RAG Engineering: design and deploy multi-step AI agents with memory and RAG pipelines.
• Workflow orchestration: build and optimize multi-step AI workflows in n8n (self-hosted).
• Enterprise API integration: develop reusable AI services via REST APIs and middleware.
• Model inference & optimization: work with Hugging Face models, embeddings, and tokenization.

Skills

Claude Code

Hugging Face models

Jupyter Notebooks

n8n self-hosted

Python

Java/Type

REST APIs

RAG

Tools

n8n

Qdrant

Weaviate

Chroma

Job description

AI Engineer (AI Agents & Automation)

Role Level: Mid–Senior Level

Domain: Generative AI, Autonomous Agents & Enterprise Automation

Role Overview

We are looking for a hands‑on AI Engineer to design, build, and deploy enterprise Generative AI applications, autonomous AI agents, and intelligent workflow automations.

In this role, you will combine agentic frameworks with low‑code orchestration using n8n, build high‑performance Retrieval‑Augmented Generation (RAG) systems, and leverage modern developer tools like Claude Code to accelerate AI implementation across our enterprise ecosystem.

Key Responsibilities

• AI Agent & RAG Engineering: Design and deploy intelligent AI agents featuring multi‑step reasoning, tool usage, memory systems, and robust RAG pipelines backed by vector databases.
• Workflow Automation & Orchestration: Build, maintain, and optimize multi‑step AI workflows in n8n (self‑hosted), including custom node creation and advanced error handling.
• Enterprise API Integration: Build reusable AI services and integrate LLM solutions with enterprise applications via REST APIs, OAuth, and custom middleware.
• Model Inference & Optimization: Work with Hugging Face models, fine‑tuning concepts, embeddings, and tokenization to optimize model performance and context usage.
• Architecture & Deployment: Collaborate with infrastructure and engineering teams to prototype, deploy, and scale enterprise‑grade AI solutions in Linux CLI environments.

Required Skills & Experience

Must‑Have AI & Automation Skills

• AI Tooling & Coding: Hands‑on experience with Claude Code, Hugging Face models, and Jupyter Notebooks.
• Workflow Orchestration: Deep experience with n8n (self‑hosted)—complex workflows, custom nodes, and error handling.
• AI Agents & RAG: Practical experience building autonomous agents (tools + memory + reasoning) and RAG architecture using vector databases (Qdrant, Weaviate, Chroma, or similar).
• Programming Languages: Proficiency in Python and/or Java / Type .

Foundational & Technical Requirements

• AI/ML Fundamentals: Solid understanding of model inference, embeddings, tokenization, and fine‑tuning concepts.
• APIs & Security: Strong grasp of REST APIs, JSON data structures, OAuth, and API key authentication.
• Environment: Comfortable working in Linux environments and CLI‑driven development workflows.
• Soft Skills: Exceptional analytical capability, debugging skills, and problem‑solving mindset.

Helius Technologies Pte Ltd

36 Robinson Road, #13-05, City House, Singapore 068877