Agentic Data Engineer

Govserviceshub; Richmond (VA); On-site; USD 80,000 - 120,000; Full time

Job summary

An innovative firm is seeking a skilled Agentic Data Engineer to drive the design and development of advanced data processing systems using cutting-edge Agentic AI technologies. The ideal candidate will possess hands-on experience with tools like LangChain and AutoGPT, alongside a robust foundation in big data engineering and ETL pipelines. This role offers the opportunity to work collaboratively with AI/ML engineers and data scientists, focusing on training and optimizing large language models while ensuring compliance with data privacy standards. Join a forward-thinking team and contribute to groundbreaking projects that shape the future of data engineering.

Qualifications

• 3+ years of experience in Python scripting and data engineering.
• In-depth experience with at least one Agentic AI framework or tool.

Responsibilities

• Develop and maintain AI-driven data processing workflows using Agentic AI frameworks.
• Design and implement ETL/ELT pipelines using Spark and Azure Databricks.

Skills

Agentic AI Tools (LangChain, AutoGPT, BabyAGI)

Python Scripting

Big Data Technologies

ETL/ELT Pipeline Development

Data Conflation

GIS Spatial Data Experience

Tools

Spark

Azure Databricks

GraphDB

Job description

Richmond, United States | Posted on 05/06/2025

Note: Only candidates local to Virginia will be considered. No relocation.

• Each candidate must submit a government-issued ID (Driver’s License or Passport) and provide three professional references (names, official emails, and phone numbers).

Job Description:

The State of Virginia (via Rice F.W. Technologies) is seeking an Agentic Data Engineer to support the design and development of intelligent data processing systems using emerging Agentic AI technologies. The ideal candidate must have hands-on experience with tools such as LangChain, AutoGPT, BabyAGI, CrewAI, and related frameworks, as well as a strong foundation in big data engineering, ETL pipelines, and LLM training.

Specialty Areas:

• Agentic AI Engineering – Experience with LangChain, AutoGPT, ReAct Framework, and other emerging agent-based AI systems.

• Big Data & ETL Development – Developing scalable ETL/ELT pipelines using Spark, Databricks, and GraphDB.

• LLM Training & Optimization – Preparing and managing structured/unstructured datasets for training Large Language Models.

• Python Development – Advanced scripting and automation capabilities for AI and data workflows.

• Data Conflation & Partitioning – Expertise in handling and integrating complex datasets with spatial and temporal properties.

• GIS & Spatial Data – Working with geographic data sets and integrating them into analytical models.

Responsibilities:

• Develop and maintain AI-driven data processing workflows using Agentic AI frameworks.

• Design and implement ETL/ELT pipelines using Spark, Azure Databricks, and GraphDB.

• Train and fine-tune LLMs using real-world structured and unstructured datasets.

• Implement data conflation techniques to merge and reconcile datasets from multiple sources.

• Collaborate with AI/ML engineers, data scientists, and GIS experts.

• Write high-quality, maintainable Python scripts for automation and data transformation.

• Ensure compliance with data privacy and governance requirements.

• Document processes and maintain version-controlled repositories for reproducibility.

Skill Matrix:

Skill

Experience (Years)

Agentic AI Tools (e.g., LangChain, AutoGPT, BabyAGI, etc.)
Required

Big Data Technologies
1+

ETL/ELT Pipeline Development
1+

Spark, GraphDB, Azure Databricks
1+

Data Partitioning
1+

Data Conflation
3+

Python Scripting
3+

LLM Training with Structured/Unstructured Data
2+

GIS Spatial Data Experience
3+

Mandatory Requirements:

• In-depth experience with at least one Agentic AI framework or tool (LangChain, AutoGPT, etc.).

• Local to Virginia with ability to attend in-person interviews.

• Minimum 3 years of Python scripting and data engineering experience.

• Experience integrating GIS spatial data into data processing workflows.

Qualifications:

• Familiarity with multiple Agentic AI tools and their orchestration.

• Understanding of AI model optimization and fine-tuning techniques.

• Prior experience in a state or local government environment.

Submission Requirements:

• Three professional references (Names, official emails, phone numbers)