Data Engineer Agentic AI & Python

Data Engineer Agentic AI & Python

Location: Alpharetta, GA

Job Summary

We are seeking a highly skilled Data Engineer with Agentic AI and Python expertise to design, develop, and deploy scalable data platforms and AI-powered solutions. The ideal candidate will have strong experience in Data Engineering, Python development, cloud-based data platforms, and modern Generative AI/Agentic AI frameworks.

Key Responsibilities

• Design, build, and maintain scalable ETL/ELT pipelines using Python, PySpark, Databricks, and Snowflake.
• Develop and optimize data ingestion, transformation, and orchestration workflows.
• Build Agentic AI solutions leveraging frameworks such as LangGraph, CrewAI, AutoGen, Semantic Kernel, or LangChain.
• Design and implement Retrieval-Augmented Generation (RAG) architectures, vector search, and semantic retrieval solutions.
• Integrate LLMs (OpenAI, Azure OpenAI, Claude, Gemini, etc.) into enterprise applications.
• Develop REST APIs and microservices using Python (FastAPI/Flask).
• Work with structured and unstructured data from multiple sources.
• Implement data quality, governance, monitoring, and observability frameworks.
• Collaborate with Data Scientists, Architects, and Business Stakeholders to deliver AI-driven solutions.
• Follow Agile/Scrum methodologies and contribute to code reviews and best practices.

Required Skills

• 7+ years of experience in Data Engineering and Python development.
• Strong hands-on experience with:
  • Python, PySpark, SQL
  • Databricks
  • Snowflake
  • Azure Data Factory (ADF) or similar ETL tools
  • Azure/AWS/Google Cloud Platform cloud platforms
• Experience building scalable data pipelines and lakehouse architectures.
• Knowledge of Spark, Delta Lake, Airflow, Kafka, and Data Warehousing concepts.
• Experience with Git, CI/CD, and DevOps practices.

Agentic AI & GenAI Requirements

• Hands-on experience with:
  • LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or LlamaIndex
  • RAG architectures
  • Vector Databases (Pinecone, ChromaDB, Weaviate, FAISS, Azure AI Search)
  • Prompt Engineering
  • AI Agents and Multi-Agent Systems
• Experience integrating OpenAI/Azure OpenAI APIs.
• Understanding of LLMOps, AI Governance, and Responsible AI practices.

Preferred Qualifications

• Experience with Snowpark, Cortex AI, or Snowflake Cortex Search/Analyst.
• Knowledge of MLOps tools such as MLflow and Azure ML.
• Exposure to conversational AI, copilots, and intelligent automation solutions.
• Relevant cloud or Databricks certifications.

Nice to Have

• Power BI or Tableau experience.
• Real-time streaming using Kafka/Event Hubs.
• Experience with Docker and Kubernetes.
• Exposure to enterprise AI transformation initiatives.

This role combines Data Engineering, Python development, and Agentic AI implementation, making it ideal for candidates with Databricks, Snowflake, RAG, and LLM-based solution experience.