We are looking for an AI Application Engineer to design, build and scale AI-enabled business applications and use cases. The core of these use cases will be driven by LLM/SLM-based architectures within the Microsoft Azure ecosystem.

This is a fully hands-on role requiring strong expertise in Python, multi-agent AI systems and Azure- based cloud infrastructure.

The selected candidate will own the full lifecycle of AI application development-from architecture design and backend implementation to testing and production deployment.

The role involves working with Azure AI Foundry, Azure Open AI, RAG architectures, and enterprise data platforms to deliver both Proof of Concepts (PoCs) and scalable production solutions.

Key Responsibilities :

- Design and develop AI-driven applications using LLMs, RAG patterns and multi-agent orchestration concepts.

- Build, maintain and scale backend services in Python.

- Architect and deploy AI solutions within Microsoft Azure.

- Integrate AI and Python services with enterprise data sources and business systems.

- Ensure performance, reliability and production readiness of AI applications.

- Monitor, optimize and troubleshoot AI model behavior orchestration logic and system latency.

Required qualifications :

- 6 to 10 years of professional experience, including: 4+ years in software engineering or backend development roles and 2+ years in Generative AI or LLM-based application development.

- Strong proficiency in Python

- Hands-on experience integrating and configuring LLM APIs (Azure Open AI preferred)

- Experience building and deploying applications within Microsoft Azure

- Solid understanding of REST APIs, scalable system design and cloud-native architecture