Perception Validation Engineer

Define Validation Metrics: Establish rigorous, statistically sound KPIs and performance benchmarks for camera, LiDAR, Radar, and sensor-fusion perception stacks (e.g., precision/recall, mAP, latency, tracking MOTA).

Build Automated Testing Pipelines: Design and maintain scalable, automated regression testing pipelines that evaluate perception algorithms on massive real-world and synthetic datasets.

Ground Truth Generation: Oversee and optimize the creation of high-fidelity ground truth data, using automated labeling tooling, offline perception models, and manual curation.

Edge-Case Mining: Identify, categorize, and build a library of challenging real-world scenarios, sensor degradations (e.g., lens flare, heavy rain, occlusion), and long-tail anomalies to stress-test the perception system.

Root-Cause Analysis: Partner closely with the Perception ML team to debug validation failures, trace anomalies back to data or algorithmic root causes, and propose data-driven solutions. Close the loop with model training.

Simulation & Tooling Development: Collaborate with the Simulation team to develop realistic sensor models and synthetic scenarios that bridge the gap between simulation and real-world validation.

Safety Documentation: Generate comprehensive verification and validation reports to support safety cases, regulatory compliance, and software release readiness.

Education: Bachelor’s or Master’s degree in Computer Science, Robotics, Electrical Engineering, Aerospace Engineering, or a related quantitative field.

Experience: 2+ years of professional experience in testing, validation, or development of robotics/autonomous systems, or computer vision models.

Programming: Strong proficiency in Python (especially NumPy, Pandas, Pytest) and/or C++.

Data Analysis: Experience manipulating and visualizing large scale datasets (SQL, data lake queries) and utilizing statistical methods to evaluate model performance.

Domain Knowledge: Solid understanding of core computer vision concepts, deep learning principles, and spatial geometry (3D transformations, coordinate frames).

Experience with ROS / ROS2

Familiarity with cloud computing infrastructure (AWS, GCP, or Azure) and containerization (Docker, Kubernetes).

Experience with machine learning frameworks (PyTorch) and validation tools.

Understanding of functional safety standards in automotive engineering (e.g., ISO 26262, ISO 21448 / SOTIF).

Experience working with CI/CD pipelines (Jenkins, Github CI) for automated testing.