AI Data Engineer

Role Overview

We are seeking an experienced AI Data Engineer to design, develop, and deploy cutting-edge LLM-based applications. This role requires strong engineering expertise combined with hands-on experience in Generative AI, RAG pipelines, and agentic systems.

Responsibilities

• Design and develop LLM-based applications using single-agent or simple multi-agent patterns for business use cases.
• Build and maintain RAG pipelines: data ingestion, chunking, embeddings, retrieval, and response generation.
• Implement prompt engineering techniques (prompt templates, chaining, basic tool/function calling).
• Develop backend services/APIs for AI applications using Python frameworks (FastAPI / Flask / Streamlit).
• Integrate AI solutions with enterprise systems, databases, and APIs.
• Apply basic guardrails and validation checks to improve response quality and reduce hallucination.
• Work with Data Engineering teams to ensure data quality, pipeline efficiency, and proper documentation.
• Collaborate with MLOps teams for deployment, monitoring, and iterative improvements.
• Document solutions, reusable components, and best practices.

Requirements

• 4–6 years total experience, with 1+ year hands-on experience in GenAI / LLM-based applications.
• Strong hands-on experience with LLMs (Claude, OpenAI, etc.), RAG pipelines, and GPT + Agentic AI implementation.
• Experience with frameworks like LangChain, LangGraph, or similar.
• Deep understanding of LLM limitations, evaluation, and optimisation strategies.
• Strong Python/Pyspark engineering expertise (production-grade development) with proven API integration experience.
• Deep data analysis experience and handling large volumes of data.
• Experience with Fabric/Azure Databricks/Snowflake data engineering integration.
• Good exposure to Cloud platforms (Azure/AWS/GCP) and SQL.
• Familiarity with Containers, CI/CD, and monitoring.
• Prior experience in Data Engineering (ETL/ELT, pipelines, orchestration), Data Science/ML lifecycle (especially NLP), or Analytics engineering.
• Good-to-have: Exposure to model fine-tuning (LoRA/PEFT), LLM output evaluation, and familiarity with the Azure AI / Azure OpenAI / AI Search ecosystems.