Agentic Data Engineer at Govserviceshub

Job Location: Richmond, VA (Hybrid) Note: Candidates with Department of Transportation or state agency experience are strongly preferred. • 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 Virginia Department of Transportation (VDOT) is seeking an Agentic Data Engineer to design, develop, and deploy data pipelines that leverage agentic AI to solve real-world transportation data problems. The role involves architecting complex data flows, training large language models, integrating human-in-the-loop feedback systems, and managing AI data operations on cloud-based platforms.Specialty Areas:• Agentic AI Integration – Designing pipelines that enable dynamic interactions between AI agents and diverse data systems. • LLM Training & Optimization – Preprocessing structured/unstructured data, training LLMs, and enhancing performance with feedback loops. • GIS and Spatial Data Processing – Working with road topology, geo-location data, and spatial correlation using lat/long datasets. • Big Data & Cloud Engineering – Leveraging Spark, GraphDB, Databricks, and Azure services for high-volume data processing. • AI + Transportation Domain Expertise – Applying agentic solutions for what-if analysis, forecasting, correlation modeling, and decision recommendations.Responsibilities:• Design and manage robust ELT pipelines and data architectures (lakes, databases). • Implement vector databases and embedding models for retrieval-based AI. • Build feedback loops for human-in-the-loop learning in AI systems. • Train and fine-tune large language models (LLMs). • Ensure efficient data storage/retrieval through partitioning and performance optimization. • Collaborate with AI engineers and data scientists on preprocessing, modeling, and deployment. • Work with GIS spatial data for route correlation and road network analysis. • Apply machine learning and statistical techniques to analyze and format multi-source data.Skill Matrix:SkillExperience (Years)Big Data Technologies (Spark, Databricks, GraphDB)1+ELT / ETL pipeline development1+Data Partitioning Strategies1+Python Scripting3+Data Conflation3+Training LLMs with structured/unstructured data2+GIS and Spatial Data Analysis3+Azure Services (AI, OpenAI, ML, Blob, Data Lakes)1+AI Agent Frameworks & Vector Databases1+Cloud & Machine Learning Fundamentals1+Mandatory Requirements:• Strong understanding of data engineering and agentic AI concepts. • Minimum 1 year experience with Spark/Databricks and data architecture on Azure. • At least 3 years of Python scripting and spatial data experience. • Proven ability to build pipelines integrating AI agents with large datasets. • Experience with LLM training and vector databases.Qualifications:• Bachelor’s or Master’s in Computer Science, Data Science, or AI. • Prior experience with Department of Transportation data and systems. • Familiarity with embedding models, Graph DBs, and cloud AI services. • Strong communication, problem-solving, and collaborative skills.Submission Requirements:• Updated Résumé • Government-issued ID (Driver’s License or Passport) • Three professional references (Names, official emails, phone numbers)