We are looking for an AI Engineer to design, build, and run production-grade agentic AI systems that support automotive engineering workflows such as testing, root cause analysis, and failure analysis. You will build tool-calling agents, retrieval pipelines, and evaluation frameworks, and integrate them reliably with existing engineering toolchains.

Design and develop LLM-powered, tool-calling agents with bounded execution, retries, and graceful failure handling Build RAG pipelines and vector search over engineering documents, logs, and tickets Develop REST APIs and define clear API contracts for system integration Validate structured LLM outputs and implement confidence scoring and fallback logic Manage the prompt, model, and evaluation lifecycle (versioning, regression testing, A/B comparison) Set up production observability and AI quality telemetry (tracing, latency, cost, accuracy, drift) Integrate with Jira-based toolchains, SW log analysis, and telemetry/ESO evidence pipelines Apply sound software architecture and Git/CI/CD practices Collaborate with test, systems, and software teams to turn engineering problems into AI solutions

3+ years of software engineering experience, including 2+ years in AI/LLM development Strong Python software development REST API development and API contract design Agentic AI development and tool-calling agents with bounded execution and failure handling Retrieval-augmented generation (RAG) and vector search Structured LLM output validation and confidence handling Prompt, model, and evaluation lifecycle management Production observability and AI quality telemetry Git and CI/CD System integration and software architecture fundamentals Nice-to-Have Skills Databricks (Apps, Model Serving, MLflow, Unity Catalog basics) Microsoft AI Foundry MCP (Model Context Protocol) React front-end development Automotive engineering processes