Generative AI Engineer: RAG & LLM Systems

Social Multiway Sdn Bhd; Kuala Lumpur; On-site; MYR 90,000 - 150,000; Full time

Benefits offered by this job

EPF

SOCSO

Annual Leave

Medical Leave

Health Insurance

Job summary

Social Multiway Sdn Bhd is seeking an AI-focused engineer to design, develop, and implement Retrieval-Augmented Generation (RAG) systems that enhance the capabilities of conversational AI models. You will integrate large language models into mobile and web apps, build robust APIs, and optimize AI pipelines on cloud platforms.

You'll collaborate with product managers and engineers in an Agile environment, leveraging Python for backend work and adhering to scalable architecture.

Qualifications

• Proven experience building retrieval-augmented generation systems.
• Experience integrating large language models into apps.
• Strong Python backend development and data processing skills.
• API design and integration across platforms.
• Cloud deployment and scalable AI solutions.
• Agile development practices and collaboration with cross-functional teams.

Responsibilities

• Design, develop, and implement RAG systems to enhance AI models.
• Integrate LLMs with mobile and web applications for seamless UX.
• Develop and maintain robust APIs for AI services.
• Collaborate with product managers and engineers to deliver features.
• Optimize AI pipelines on cloud platforms (AWS/Azure/GCP).
• Stay updated on AI advancements and contribute to CI/CD processes.

Skills

RAG systems

LLMs integration

Python backend

APIs design

Tools

AWS

Azure

GCP

CI/CD

Job description

Social Multiway Sdn Bhd is seeking an AI-focused engineer to design, develop, and implement Retrieval-Augmented Generation (RAG) systems that enhance the capabilities of conversational AI models. You will integrate large language models into mobile and web apps, build robust APIs, and optimize AI pipelines on cloud platforms.

You'll collaborate with product managers and engineers in an Agile environment, leveraging Python for backend work and adhering to scalable architecture.