Junior AI Engineer

E-Genting Sdn Bhd; Kuala Lumpur; On-site; MYR 60,000 - 80,000; Full time

Job summary

A technology firm in Kuala Lumpur is seeking a talented AI Engineer to build a next-generation Unified AI Platform. You will manage backend systems that integrate LLM workflows, memory management, and API orchestration. Responsibilities include designing and implementing backend services in Python, maintaining RAG pipelines for AI-driven agents, and collaborating with stakeholders. Fresh graduates or candidates with 1-2 years of experience are welcome to apply.

Qualifications

• Strong proficiency in Python (3.9+) and backend development.
• Experience building APIs/web services using FastAPI, Flask, or similar frameworks.
• Understanding of LLM integration and prompt engineering.

Responsibilities

• Design and implement backend services/APIs to support AI agents.
• Build and maintain RAG pipelines including document ingestion and embedding computation.
• Collaborate with product, operations, and stakeholders to deliver production-ready features.

Skills

Python

API development

Backend development

Machine learning

Problem-solving

Memory management

Education

Bachelor’s degree in AI, Computer Science, Software Engineering, Data Science or related

Tools

FastAPI

PostgreSQL

Vector databases

Job description

We are seeking a talented and motivated AI Engineer to join our core team to build a next generation Unified AI Platform to power multiple AI-driven agents (RAG-based chatbots, API action agents, BI analytics agents, forecasting agents, etc.) for our enterprise system. You will take the ownership of building and maintaining backend systems that integrate LLM workflows, vector search / retrieval-augmented generation (RAG), memory management, API orchestration, and production-grade infrastructure.

Your work will shape the backbone of a multi-agent AI ecosystem — from document ingestion and semantic search to conversational memory, tool orchestration, and generation pipelines.

Design and implement backend services/APIs using Python (e.g. with FastAPI or similar frameworks) to support AI agents.

Build and maintain RAG pipelines: document ingestion (manuals, notes), embedding computation, vector indexing and search (vector DB or PG-vector), retrieval, ranking, LLM-based answer generation.

Integrate with LLM providers (e.g., OpenAI, Gemini, open-source LLMs) in a modular, provider-agnostic way. Maintain prompt templates, tool abstraction, and agent orchestration.

Implement memory / state management for chatbots (session memory, optional long-term memory), user history, and context persistence.

Design and manage data storage: relational data (user profiles, chat history, metadata) in PostgreSQL; NoSQL database; semantic data (embeddings, vector indices) via vector store (or PG-vector).

Design, train, and deploy machine learning models (e.g., supervised/unsupervised, deep learning) with strong understanding of model evaluation, feature engineering, and MLOps best practices.

Ensure robustness, reliability, and maintainability: error handling, logging, monitoring, performance profiling, and test coverage.

Collaborate with product, operations, and other stakeholders to translate business needs into technical workflows and deliver production-ready features.

Strong proficiency in Python (3.9+) with experience in backend development.

Experience building APIs/web services using FastAPI, Flask, or similar frameworks.

Understanding of LLM integration, prompt engineering, and LLM-based generation workflows (RAG, retrieval + generation, contextual LLM usage).

Familiarity with vector search / embeddings / vector databases — able to work with vector stores (pgvector, Chroma, FAISS, Qdrant, etc.) or relational-vector hybrid storage.

Solid knowledge of relational databases (PostgreSQL or similar), schema design, indexing, and data modeling.

Good software engineering practices: modular code design, version control (Git), documentation, testing, and code reviews.

Ability to design and maintain asynchronous workflows, background tasks, and efficient data pipelines (embedding generation, indexing, retrieval, memory).

Problem-solving mindset — ability to debug complex issues, design fallback logic (e.g., hallucination detection, fallback LLM responses), and ensure system reliability.

Bachelor’s degree in Artificial Intelligence, Computer Science, Software Engineering, Data Science, or related field (or equivalent experience).

Fresh graduates or candidates with 1-2 years of AI-related software development experience are welcome.