AI Engineer

As a Full Stack AI Engineer, you will bridge the gap between core software engineering and applied artificial intelligence. You will help us unlock the next generation of supply chain intelligence by integrating multi-agent workflows and LLM-driven features directly into Sensos’ core platform.

Responsibilities:

• Spearhead the architecture, development, and deployment of autonomous AI agents designed to make supply chain data more accessible, automate complex decision-making, and streamline system diagnostics.
• Build and deploy scalable full-stack features using modern frameworks, overseeing all engineering aspects from prompt orchestration to backend logic.
• Develop and maintain retrieval-augmented generation (RAG) pipelines and multi-agent workflows.
• Partner with backend engineering teams to ensure real-time sensor data pipelines (e.g., Azure Event Hubs) seamlessly support AI workloads.
• Champion code quality and system health by implementing robust observability for both standard microservices and AI model performance in production.
• Actively utilize AI-driven development tools (like Claude, Cursor) to accelerate coding, debugging, and testing.
  
  

• 4+ years of industry experience in application development (SaaS products in a cloud-native environment).
• Hands-on expertise with modern programming languages and distributed, cloud-native architectures.
• Demonstrated experience delivering production-grade LLM-based systems, specifically working with prompt engineering, agent frameworks, and RAG architectures.
• Knowledge and experience with principles of fault tolerance, resiliency, and event-driven microservices architecture.
• Familiarity with streaming data, time-series analysis, or processing IoT telemetry data at scale is a strong bonus.
• Experience with cloud ecosystems, ideally Azure and Azure OpenAI services.
• Hands-on experience with Terraform & Kubernetes – Advantage.