Sr. Specialist - AI Automation & Testing

What you’ll do

• Own and build the infrastructure that enables rapid, reliable iteration of vehicle software and electronics.
• Develop and implement toolchains spanning: Code commit → build → ECU flashing → vehicle/HIL testing → data logging → analysis.
• Build ML models for test case prioritization, failure prediction, and intelligent test selection.
• Implement anomaly detection on logs, CAN traces, and system telemetry.
• Develop NLP pipelines for automated log triage and defect classification.
• Integrate AI modules into pipelines using Jenkins / GitLab CI / GitHub Actions.
• Orchestrate workflows with Docker + Kubernetes for scalable test execution.
• Implement event-driven automation (e.g., build triggers, test triggers, auto triage).
• Embed quality gates based on AI predictions (e.g., block/allow release based on risk scoring).
• Automate ECU flashing (UDS, bootloaders) across benches and vehicles and OTA package generation and deployment workflows.
• Automate smoke validation pipelines post-integration with real-time analytics.
• Support pre-release (e.g., Pilot Hall / factory SW integration) with AI-based readiness scoring.
• Align AI automation with DVP, sprint cycles, and regression frameworks.
• Create dashboards for release health, defect leakage, and test effectiveness.

What you’ll bring

• A Master’s degree in Computer Science, Electrical/Electronics Engineering, or a related field with 8+ years of experience.
• Strong understanding of vehicle E/E architecture and ECU-level software stacks, automotive communication protocols (CAN, LIN, FlexRay, Ethernet), UDS diagnostics (ISO 14229) and diagnostic communication tools.
• Expert knowledge of GitHub/GitLab, Jenkins, and Artifactory. ALM/PLM proficiency in Codebeamer, Siemens Polarion, IBM DOORS Next Gen, or PTC Windchill.
• Programming: Python (advanced), SQL, Bash.
• ML/AI: n8n, Pinecone, Scikit-learn, TensorFlow/PyTorch, time-series & anomaly detection with CI/CD expertise in Jenkins, GitLab CI, GitHub Actions.
• Containers/Orchestration: Docker, Kubernetes.
• Strong understanding, development and scaling of vehicle toolchain, data systems across fleet for development and analytics.
• Strong understanding of 1st principles in Engineering, result/solution oriented.
• Familiarity with SW for embedded systems, EE systems and architecture.
• Familiarity with A2B, CAN, Automotive Ethernet, LIN, LVDS communication protocols and Vehicle Network tools, such as CANalyzer, CANoe, etc.
• Expertise with complex problem solving, data analysis, access/interpret/drive results with extended teams.
• Knowledge of Automotive design and development process, system requirements, and general engineering best practices.