Junior Agentic AI Engineer

About the Role

Tapway Sdn Bhd, is looking for an Agentic AI Engineer to join our AI team in Sri Petaling, Kuala Lumpur.

You will design, build, and deploy LLM-powered agentic AI systems that can reason, use tools, retrieve information, and automate complex business tasks. You will work closely with product and engineering teams to turn AI prototypes into reliable, scalable, production-ready solutions.

This is an exciting opportunity for an AI engineer who enjoys working hands-on with Large Language Models (LLMs), RAG, AI agents, and emerging AI technologies.

Key Responsibilities

• Design and build LLM-powered AI agents and multi-agent workflows using tool calling, planning, memory, and other agentic capabilities.
• Develop Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embeddings, vector search, and re-ranking.
• Integrate LLMs through cloud APIs and self-hosted inference platforms such as vLLM, with consideration for latency, cost, scalability, and performance.
• Build evaluation frameworks, guardrails, and monitoring mechanisms to measure AI accuracy, reliability, performance, and safety.
• Develop APIs and integrations to connect AI agents with business applications, databases, and external tools.
• Prototype and experiment with emerging AI technologies, then convert successful prototypes into production-ready AI features.
• Troubleshoot, evaluate, and optimise AI applications for performance, reliability, and scalability.
• Collaborate closely with Product Managers, AI/ML engineers, software engineers, and other stakeholders to translate business requirements into practical AI solutions.
• Document system architecture, technical processes, experiments, and implementation details.
• Keep up to date with developments in LLMs, agentic AI, RAG, AI infrastructure, and machine learning and evaluate their potential applications.

What We Offer

At Tapway, you will have the opportunity to work on real-world AI applications and gain hands-on exposure to the rapidly evolving field of agentic AI.

We provide:

• Competitive compensation based on experience and qualifications
• Opportunities to work with LLMs, AI agents, RAG, and AI deployment technologies
• Exposure to real-world AI product development
• Professional development and continuous learning opportunities
• Collaborative and innovative working environment
• Opportunities to work closely with experienced product and engineering teams
• Career growth within the ITMAX Group

About Tapway

Tapway Sdn Bhd is an AI technology company within the ITMAX Group, focusing on AI-powered solutions that help businesses transform operations through intelligent automation and computer vision technologies.

Our team works at the intersection of AI, software engineering, computer vision, and automation, developing practical technology solutions for real-world business and operational challenges.

If you are passionate about LLMs, agentic AI, RAG, and building intelligent systems, we would love to hear from you.

Apply Now

Please submit your updated CV and, where applicable, include links to your GitHub, portfolio, or AI/LLM projects demonstrating your practical experience.

Requirements

Qualifications & Requirements

Education

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related field.
• Candidates with equivalent practical industry experience may also be considered.

Experience

• Minimum 1 year of hands-on experience in developing ML, LLM, or AI applications.
• Internship experience is considered relevant, particularly where candidates have developed practical AI/ML projects.
• Experience building RAG systems, AI agents, LLM applications, or similar AI solutions will be an advantage.

Skills & Competencies

• Strong programming skills in Python.
• Hands-on experience with LangChain, LangGraph, or similar AI/agent frameworks.
• Good understanding of Large Language Models (LLMs) and prompt engineering.
• Practical experience developing RAG pipelines, vector search, embeddings, and vector databases.
• Familiarity with tool calling, agent workflows, memory, and multi-agent systems.
• Experience with vLLM or other LLM inference/deployment technologies is an advantage.
• Experience with Docker and deploying applications to cloud or on-premise environments.
• Good understanding of software engineering principles, APIs, Git, and system integration.
• Strong analytical and problem-solving skills.
• Ability to work collaboratively with product and engineering teams.
• Passion for experimenting with emerging AI technologies and turning ideas into practical solutions.

Skills

LLM Application, AI Agents, AI Agent Monitoring, Cloud Deployment