AI Engineer

GALMON (S) PTE LTD; Singapore; On-site; SGD 90,000 - 130,000; Full time

Job summary

GALMON (S) PTE LTD is seeking an In-House AI Engineer to drive internal and product AI transformation. You will embed AI into our core web portal and build tools to boost team efficiency across departments.

You will work with internal teams to identify bottlenecks and transform existing software features into intelligent, automated systems.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Information Technology, or related field.
• 3+ years software engineering experience including AI capabilities integration.
• Hands-on experience with LLM APIs, RAG apps, and vector DBs.

Responsibilities

• Core Portal Integration: deploy AI features into the web platform.
• Internal Process Automation: design AI tools and automation scripts.
• PoCs with generative AI and API integrations.
• API & System Integration: connect external AI services to backend.

Skills

Full-stack development

Python

TypeScript

React/Vue

REST APIs/GraphQL

AI integration

Vector databases

Workflow automation

Docker

Cloud deployment

Education

Bachelor's degree in Computer Science / IT

Tools

Pinecone

Qdrant

Chroma

pgvector

n8n

Make

LangChain

LlamaIndex

Docker

AWS

GCP

Azure

Job description

We are looking for an In-House AI Engineer to drive our internal and product AI transformation. In this hands-on role, you will take ownership of identifying manual workflows, embedding AI solutions directly into our core web portal, and building custom tools that boost team efficiency across departments.

You will work directly with internal teams to understand operational bottlenecks and transform existing software features into intelligent, automated systems.

Key Responsibilities

• Core Portal Integration: Architect, test, and deploy AI features (e.g., intelligent search, automated tagging, contextual summaries, predictive tools) directly into our web platform.
• Internal Process Automation: Identify repetitive, time-consuming manual workflows across teams and design custom AI tools, automation scripts, or smart workflows to streamline operations.
• Solution Scoping & Prototyping: Rapidly build and evaluate Proof-of-Concepts (PoCs) using generative AI, API integrations, and open-source models to evaluate ROI before full rollout.
• API & System Integration: Connect external AI services (OpenAI, Anthropic, Google Gemini, etc.) and open-source models with existing backend infrastructure, databases, and microservices.
• Performance & Cost Management: Optimize AI model latency, API usage costs, and response accuracy to maintain high reliability and cost efficiency.
• Internal AI Support & Training: Act as the internal Subject Matter Expert (SME), guiding technical and non-technical staff on best practices for adopting AI tools safely and effectively.

Qualifications & Requirements

• Education: Bachelor's degree in Computer Science, Software Engineering, Information Technology, or a related technical field (or equivalent practical experience).
• Core Software & AI Skills:
• Software Engineering: Strong background in full-stack or backend web development (Python, Node.js/TypeScript, React/Vue, REST APIs/GraphQL).
• AI/LLM Integration: Hands-on experience integrating LLM APIs, building RAG (Retrieval-Augmented Generation) applications, and working with vector databases (Pinecone, Qdrant, Chroma, pgvector).
• Automation Tools: Familiarity with workflow automation platforms (n8n, Make, LangChain, LlamaIndex) and API orchestration.
• Cloud & DevOps: Experience deploying web services on AWS, GCP, or Azure using Docker.
• 3+ years of overall software engineering experience, with at least 1-2 years focused on integrating AI capabilities into production applications.