Data Engineer: AI-Driven Pipelines & Modernization

KellyMitchell Group; McLean (VA); Hybrid; USD 72,000 - 103,000; Full time

Benefits offered by this job

Medical Insurance

Dental Insurance

Vision Insurance

ESOP

401K

Job summary

KellyMitchell is seeking a Data Engineer for a contract role supporting vendor modernization initiatives. The candidate will migrate tools to Spark/Scala, build data pipelines, and enable AI/ML workflows in a hybrid work environment.

The position focuses on comparing legacy systems with target architectures, developing automated data workflows, and collaborating with cross-functional teams to deploy AI models and MCP-enabled backend processes.

Qualifications

• Advanced Python for data manipulation, automation, and AI development.
• Hands-on Spark and Scala for large-scale processing and migration.
• Experience building stateful multi-agent apps with LangGraph and LLMs.
• Knowledge of MCP and integrating AI models with external tools.
• Deep understanding of generative AI frameworks and deployment.
• Expertise in prompt design, testing, and optimization.
• Experience with CI/CD, automated testing, and modern deployment practices.

Responsibilities

• Compare data structures across legacy and target systems to identify gaps.
• Build automated tools and pipelines to correct data discrepancies.
• Migrate legacy tools to modern Spark and Scala ecosystems.
• Design data pipelines to ingest, process, and clean data for ML models.
• Support feature development within a team of data engineers.
• Collaborate to integrate AI models into backend workflows.

Skills

Python

Spark

Scala

LangGraph

LLMs

MCP

Generative AI

Prompt engineering

CI/CD

Job description

KellyMitchell is seeking a Data Engineer for a contract role supporting vendor modernization initiatives. The candidate will migrate tools to Spark/Scala, build data pipelines, and enable AI/ML workflows in a hybrid work environment.

The position focuses on comparing legacy systems with target architectures, developing automated data workflows, and collaborating with cross-functional teams to deploy AI models and MCP-enabled backend processes.