AI Engineer

Position Summary

Your role will involve the development, automation, and deployment of enterprise-level AI systems. You will primarily focus on the creation of intelligent AI agents, establishing connections between systems through n8n workflows, and utilizing RAG pipelines to efficiently retrieve custom data, thereby streamlining business processes for automation.

Key Responsibilities

• Development of AI Agents & RAG: Design and implement intelligent bots that can utilize tools, retain context, and access real-time enterprise data via vector databases.
• Workflow Automation: Create comprehensive, error-resistant automation processes using n8n (preferably self-hosted) along with custom nodes.
• System Integration: Integrate AI solutions with existing enterprise applications through REST APIs.
• Deployment & Optimization: Collaborate with technical teams to deploy scalable AI models in Linux environments, address troubleshooting issues, and prototype new AI functionalities.

Required Skills

• AI & ML Technologies: Proficiency in Claude Code, Hugging Face, vector databases (such as Qdrant, Chroma, Weaviate), and Jupyter Notebooks.
• Programming & Tools: Strong command of Python and/or JavaScript/TypeScript, Linux/CLI, and custom n8n workflow design.
• Fundamental Concepts: In-depth understanding of LLM principles (embeddings, tokenization, model inference, fine-tuning) and API standards (REST, JSON, OAuth).

Important Information:

• Please submit your resume in Word format to [HIDDEN TEXT]
• If this opportunity does not align with your skills, feel free to refer it to others who might be interested.
• For a confidential discussion, interested candidates can contact me at +65- 6950 5535.