The Agentic Data Engineer serves as a technical expert within the vehicle product engineering team, designing and scaling industrial-grade data and AI platforms. This role involves developing self-healing, agentic data and decision systems that monitor vehicle design processes, detect anomalies, and proactively recommend actions to improve safety and quality. Key responsibilities include defining technical roadmaps, establishing reference architectures for batch and streaming pipelines, and leading the implementation of agentic workflows using LLMs and ML models. The position requires proficiency in Python, Scala, and Java, alongside experience with LangGraph, AutoGen, Semantic Kernel, or LlamaIndex. The work focuses on modernizing global vehicle design processes by creating robust, production-grade services that manage complex data from systems like Team Center to solve ambiguous engineering problems.
Design and build industrial-grade data and AI platforms to power vehicle product engineering.
Define the technical roadmap for agentic automation and vehicle product engineering data.
Establish reference architectures for high-reliability batch and streaming data pipelines.
Design and lead the implementation of agentic workflows using LLMs and ML models.
Develop production-grade services with clear SLAs, feedback loops, and human-in-the-loop controls.
Define enterprise-level patterns for data ingestion, quality rules, and semantic modeling.
Mentor senior and staff-level engineers through design reviews and architecture forums.
Translate complex technical concepts into decision frameworks for senior leadership.
What we're looking for
Bachelor’s in Computer Science, Data Engineering, Electrical/Mechanical/Industrial Engineering, or related technical field; or equivalent industry experience.
Master’s degree in Computer Science, Data Engineering, Electrical/Mechanical/Industrial Engineering, or related technical field; or equivalent industry experience (preferred).
12+ years of industry experience delivering large-scale solutions and leading technical direction in relevant domains.
8+ years of experience in data engineering or closely related roles.
Mastery in designing and operating large-scale data platforms (batch + streaming) on cloud infrastructure.
Experience building reliable, observable pipelines in Python, Scala, or Java using modern orchestration and workflow tools.
Proficiency in data modeling (relational, columnar, time-series) and performance optimization for analytics, ML, and real-time decisioning.
Strong literacy in data science and ML, including experience with LangGraph, AutoGen, Semantic Kernel, or LlamaIndex.
Python
Large Language Models
Microsoft Azure
Vector Databases
APIs
Agile
CI/CD
Containerization
Infrastructure as Code
GitHub Copilot
Claude Code
System Design
DevOps