AI Engineer: LLMs & RAG for Scalable Apps

ATS Client; Pretoria; Hybrid; ZAR 432,000 - 720,000; Full time

Job summary

ATS Client in Pretoria is seeking an Intermediate AI Engineer to design and deliver AI-powered solutions that leverage LLMs, RAG, and autonomous agents. You will work on scalable architectures and modern AI systems, collaborating with cross-functional teams to deploy reliable AI applications.

The candidate will build vector search and data pipelines, optimise costs and latency, and implement cloud-based platforms with Docker/Kubernetes, FastAPI, and PostgreSQL.

Qualifications

• Bachelor’s degree or equivalent in CS/Engineering or related tech field.
• 4+ years of professional software development experience.
• Hands-on experience building or deploying LLM-powered apps, AI agents, or intelligent automation.

Responsibilities

• Design, develop, and deploy robust AI applications including agent-based systems and RAG architectures.
• Build and optimise vector search solutions for large datasets.
• Evaluate LLM strategies including fine-tuning, RAG, context management, and cost/performance optimisations.
• Develop scalable backend services and APIs with Python (FastAPI/Flask).
• Architect and maintain cloud-based AI platforms on AWS or Azure with cloud-native tools.
• Implement containerisation/orchestration with Docker, Kubernetes, or ECS and IaC practices.
• Design and manage data architectures (PostgreSQL; optional NoSQL integration).
• Apply microservices and event-driven architectures with clean code practices.
• Collaborate with frontend/product teams to integrate AI features into web apps.

Skills

Software development

LLM experience

Cloud platforms

Distributed systems

Education

Bachelor's degree in Computer Science, Engineering, or a related technology discipline

Tools

Docker

Kubernetes

FastAPI

PostgreSQL

Job description

ATS Client in Pretoria is seeking an Intermediate AI Engineer to design and deliver AI-powered solutions that leverage LLMs, RAG, and autonomous agents. You will work on scalable architectures and modern AI systems, collaborating with cross-functional teams to deploy reliable AI applications.

The candidate will build vector search and data pipelines, optimise costs and latency, and implement cloud-based platforms with Docker/Kubernetes, FastAPI, and PostgreSQL.