PlusAI is a Physical AI company pioneering AI-based virtual driver software for factory-built autonomous trucks. Headquartered in Silicon Valley with operations in the United States and Europe, Plus was named by Fast Company as one of the World’s Most Innovative Companies. Partners including TRATON GROUP’s Scania, MAN, and International brands, Hyundai Motor Company, Iveco Group, Bosch, and DSV are working with Plus to accelerate the deployment of next-generation autonomous trucks. If you’re ready to make a huge impact and drive the future of autonomy, Plus is looking for talented individuals to join its fast-growing teams.
As a Perception Validation Engineer, you will be responsible for defining, developing, and executing the validation strategies that ensure our autonomous vehicles (AVs) perceive the world with absolute accuracy and reliability.
You will sit at the intersection of cutting-edge AI and rigorous systems engineering. Your mission is to design automated pipelines, establish performance metrics, and build the testing frameworks necessary to ruthlessly evaluate our machine learning models (BEV based) against real-world edge cases. If you love breaking complex AI systems to make them unbreakably safe, this role is for you.
Your opportunities joining PlusAI
Work, learn and grow in a highly future-oriented, innovative and dynamic field.
Wide range of opportunities for personal and professional development.
Catered free lunch, unlimited snacks and beverages.
Highly competitive salary and benefits package, including 401(k) plan.
•
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.