Data Engineer 2

About the Role We are looking for a Data Engineer II with hands-on data engineering experience and a growing passion for Agentic AI to join our Azara Data & AI Engineering team at JLL Technologies. You will build and maintain data pipelines, transformation workflows, and data services that power Azara, our AI-driven data intelligence platform for commercial real estate while actively developing AI-augmented and agentic capabilities to make those workflows smarter, self-healing, and more autonomous. This role is ideal for a data engineer who wants to go beyond traditional pipelines and apply Agentic AI to real-world data engineering challenges at enterprise scale. Key Responsibilities Data Engineering & Pipeline Development Design, build, and maintain scalable data ingestion, transformation, and serving pipelines using Python and PySpark on Databricks Develop data services and APIs (FastAPI) that expose curated data assets to downstream applications and AI services Write and optimize SQL for data transformation, aggregation, and quality validation across large-scale datasets Implement pipeline monitoring, alerting, and data quality checks to ensure reliability and SLA compliance Manage data workflows using orchestration tools (Azure Data Factory, Airflow, or Databricks Workflows) Agentic AI Integration Build AI agents that automate data engineering tasks such as self-healing pipelines, anomaly detection, and automated data quality remediation Develop agentic workflows using LangGraph or LangChain that integrate with data platforms and enterprise data sources Implement LLM-powered natural language to data query capabilities (e.g., Databricks Genie-style interactions) for data access layers Integrate LLM APIs (Azure OpenAI) into data services for intelligent data enrichment, classification, and summarization Collaborate with AI engineers to deploy RAG pipelines that leverage data assets as knowledge sources for agent workflows Data Platform & Cloud Infrastructure Build and maintain data models, Delta Lake tables, and lakehouse architecture components on Databricks and Azure Implement data access patterns, caching (Redis), and partitioning strategies for efficient data serving Develop event-driven data workflows using Azure Service Bus and Dapr for real-time pipeline triggers Assist in distributed task processing (Celery) for scalable, async data workloads Contribute to CI/CD pipelines and infrastructure-as-code for data platform components Quality & Engineering Practices Write unit tests and integration tests (pytest) for pipeline logic, data transformations, and AI-integrated components Participate in code reviews with attention to data quality, pipeline reliability, and AI-specific concerns (hallucination, cost, prompt safety) Implement structured logging and observability for pipeline health and AI workflow performance Follow data governance, security, and compliance practices for enterprise data handling Collaboration & Growth Collaborate with senior data engineers, AI engineers, and product managers in an Agile environment Document data models, pipeline design decisions, and agentic workflow patterns Participate in GenAI knowledge-sharing sessions and actively upskill in emerging Agentic AI frameworks and techniques Progressively take ownership of data domains and pipeline components with increasing independence Required Qualifications 3 5 years of professional data engineering experience with strong proficiency in Python and SQL Hands-on experience building and maintaining data pipelines on a cloud data platform (Databricks, Azure Synapse, or equivalent) Working experience with PySpark or equivalent distributed data processing framework Experience with data orchestration tools (Azure Data Factory, Airflow, Databricks Workflows, or similar) Familiarity with Delta Lake, lakehouse architecture, or similar open table formats 1+ year of hands-on experience with AI/ML integration, LLM APIs, or agent frameworks (LangGraph, LangChain, or equivalent) Experience with Python web frameworks (FastAPI preferred) for building data services and APIs Experience with AI-powered development tools (Cursor AI, GitHub Copilot, or similar) for AI-augmented development across the SDLC Familiarity with Git version control and collaborative development workflows Basic understanding of Microsoft Azure cloud platform Preferred Qualifications Experience with Databricks Genie or natural language to SQL query platforms Familiarity with vector databases (Qdrant, PgVector, ChromaDB) for RAG pipeline integration Exposure to LangGraph multi-agent orchestration for data automation workflows Experience with event-driven patterns (Azure Service Bus, Dapr) and real-time streaming Familiarity with Azure cloud services (Data Lake, Azure Data Factory, Key Vault, Blob Storage) Experience with distributed task processing (Celery, Redis) for async data workloads Familiarity with containerization (Docker) and Kubernetes for data service deployment Exposure to data governance frameworks, data cataloging tools, or data quality platforms Familiarity with observability tools (Datadog, LangSmith) for pipeline and AI workflow monitoring Technical Skills & CompetenciesData Engineering Languages: Python, SQL, PySpark Platforms: Databricks (Delta Lake, Workflows, Genie) Cloud: Azure (Data Lake, ADF, Blob Storage, Key Vault) Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.