About Aarvian
Aarvian is a "Process-First" AI transformation partner. We specialize in moving global Retailers from fragmented data to Agentic Workflows. We don't build "Black Boxes"; we build bespoke AI solutions directly on our clients' native stacks to drive measurable P&L; impact.
The Role
As an AI Engineer at Aarvian, you will be responsible for the hands-on development of AI agents and LLM-powered applications. Working within a high-caliber squad of Data Engineers and Scientists, you will turn retail business logic into production-ready code using the Azure Databricks Lakehouse.
Key Responsibilities
• Hands-on Agent Development: Build and iterate on multi-agent workflows (using LangChain or CrewAI) that solve specific retail functions like automated stock replenishment or personalized marketing copy generation.
• Lakehouse Integration: Develop and maintain data pipelines using PySpark and Delta Live Tables to feed high-quality data into AI models.
• RAG Implementation: Build and optimize Retrieval-Augmented Generation (RAG)
systems using Azure AI Search and Databricks Vector Search to ensure agents have real-time access to retail catalogs.
• Model Deployment: Deploy LLMs and custom models via Databricks Model Serving (Mosaic AI) and manage the lifecycle using MLflow.
• Client Tech-Stack Alignment: Ensure all code is written to run natively within the client’s Azure environment, adhering to strict data security and Unity Catalog governance.
Technical Requirements (The "Must-Haves")
• Experience: 3–5 years of qualified experience in a Data Science or AI Engineering role.
• Coding: Strong proficiency in Python (clean, modular code) and SQL.
• Big Data: 1+ year of hands-on experience with PySpark and Databricks.
• GenAI: Proven experience building at least one LLM-based application (using OpenAI, Llama, or similar) beyond a simple tutorial.
• Cloud: Familiarity with the Azure portal (Blob Storage, Key Vault, Entra ID). What We Look For (The "Aarvian" DNA)
• The