AI Engineer

GARENA ONLINE PRIVATE LIMITED; Singapore; On-site; SGD 90,000 - 150,000; Full time

Job summary

Garena Online Private Limited is seeking an AI Engineer to build and operate production-grade AI Agent capabilities for Spark. You will work on LLM orchestration, backend services, enterprise integrations, memory and evaluation systems, owning features from design through production deployment.

Responsibilities include designing, building, and deploying LLM-powered applications, exploring models, and collaborating with Product Managers and Designers to translate needs into practical AI

Qualifications

• Bachelor's degree or higher in a related field.
• Hands-on experience building AI/LLM applications.
• Experience with RAG architectures and related frameworks.
• Familiarity with APIs, databases, and cloud platforms.

Responsibilities

• Design, build, and deploy LLM-powered applications and AI agents.
• Deliver end-to-end product solutions and experiment with models and frameworks.
• Develop AI workflows using RAG, tool calling, and prompt engineering.
• Collaborate with Product Managers and Designers to translate user needs into solutions.
• Prototype quickly and validate ideas with experiments and user feedback.
• Optimize AI systems for accuracy, latency, and cost.
• Deploy and maintain AI solutions in production, with monitoring and improvements.
• Stay updated on LLMs, generative AI, and AI agent technologies.

Skills

Python

LLM / Generative AI

Prompt engineering

RAG architectures

APIs & Cloud

Problem solving

Team collaboration

Education

Bachelor's degree in Computer Science / AI / Computer Engineering / Data Science

Tools

LangChain

LangGraph

Job description

Spark is an enterprise AI assistant embedded in our communication suites. It helps employees understand conversations, access workplace knowledge, communicate effectively, and complete tasks across enterprise tools. We are looking for an AI Engineer to build and operate production-grade AI Agent capabilities for Spark. You will work across LLM orchestration, backend services, enterprise integrations, memory and evaluation systems, owning features from design through production deployment.

Job Description:

• Design, build, and deploy LLM-powered applications and AI agents
• End to end product delivery, experimenting with different models, frameworks, and approaches to identify the best solution for specific product and business requirements.
• Develop AI workflows using techniques such as RAG, tool calling, function calling, agentic workflows, and prompt engineering.
• Collaborate closely with Product Managers and Designers to translate user needs into practical AI solutions.
• Prototype and iterate quickly, using experiments and user feedback to validate ideas before productionising them.
• Optimise AI systems for accuracy, scalability, latency, and cost.
• Take ownership of deploying and maintaining AI solutions in production, including monitoring performance and continuously improving the system.
• Stay up to date with developments in LLMs, generative AI, and AI agent technologies, and identify opportunities to apply emerging techniques to our products.

Job Requirements:

• Bachelor's degree and above in Computer Science, Artificial Intelligence, Computer Engineering, Data Science or a related field.
• Relevant full time or internship experience in AI/LLM engineering roles
• Strong programming skills in Python
• Hands‑on experience building applications using LLMs or Generative AI.
• Hands‑on experience with RAG architectures and frameworks such as LangChain or LangGraph
• Familiarity with APIs, databases, cloud platforms, and deploying applications to production.
• Strong problem‑solving skills and the ability to evaluate technical trade‑offs between quality, cost, latency, and complexity.
• Comfortable working in a fast‑moving environment where requirements and AI technologies evolve rapidly.