<div><div><div><div><strong>XPENG</strong> is a leading smart technology company at the forefront of innovation, integrating advanced AI and autonomous driving technologies into its vehicles, including electric vehicles (EVs), electric vertical take-off and landing (eVTOL) aircraft, and robotics. With a strong focus on intelligent mobility, XPENG is dedicated to reshaping the future of transportation through cutting-edge R&amp;D in AI, machine learning, and smart connectivity.</div>About the Role<div>We are looking for a strong <strong>Machine Learning Engineer</strong><strong> / </strong><strong>Computer Vision</strong><strong> Engineer</strong> to work on <strong>Traffic Sign Recognition</strong><strong> (</strong><strong>TSR</strong><strong>) 2D detection</strong> for production autonomous driving systems.</div><div>In this role, you will be responsible for the full lifecycle of TSR model development, including <strong>scenario analysis, data preparation, model training, evaluation, </strong><strong>optimization</strong><strong>, quantization, and deployment</strong>. You will work closely with perception, data, infrastructure, and deployment teams to improve traffic sign detection performance across diverse real-world driving scenarios.</div><div>This role is ideal for candidates who enjoy solving practical computer vision problems, building reliable model iteration pipelines, and bringing perception models from offline training to onboard production systems.</div>What You’ll Do<ul><li><div>Develop and improve <strong>2D traffic sign detection models</strong> for autonomous driving perception systems.</div></li><li><div>Analyze TSR-related scenarios and failure cases, including missed detections, false positives, occlusions, small objects, rare signs, region-specific signs, and adverse weather or lighting conditions.</div></li><li><div>Prepare, clean, curate, and analyze training and evaluation datasets for TSR model iteration.</div></li><li><div>Design and execute model training experiments, including data sampling, augmentation, loss tuning, class imbalance handling, and hard-case mining.</div></li><li><div>Build and maintain evaluation pipelines for TSR models, including offline metrics, scenario-based evaluation, regression testing, and error analysis.</div></li><li><div>Collaborate with data teams to define mining strategies for long-tail TSR scenarios and improve dataset coverage.</div></li><li><div>Optimize models for production deployment, including <strong>ONNX / TensorRT / quantization / inference acceleration</strong>.</div></li><li><div>Work with deployment and platform teams to validate model performance on onboard or edge compute platforms.</div></li><li><div>Track model performance across versions and support continuous improvement through data-model-evaluation feedback loops.</div></li><li><div>Debug issues across the full stack, including data quality, labeling, model behavior, evaluation mismatch, and deployment consistency.</div></li></ul>Basic Qualifications<ul><li><div>Master’s, or PhD degree in Computer Science, Electrical Engineering, Robotics, Computer Vision, Machine Learning, or a related field.</div></li><li><div>3-5 years of strong hands-on experience with <strong>computer vision</strong><strong> models</strong>, especially object detection.</div></li><li><div>Experience with detection architectures such as <strong>YOLO</strong><strong>, Faster R-CNN, DETR/Deformable DETR, RT-DETR, RTMDet</strong>, or similar models.</div></li><li><div>Proficiency in <strong>Python</strong> and deep learning frameworks such as <strong>PyTorch</strong> or TensorFlow.</div></li><li><div>Solid understanding of object detection training workflows, including dataset preparation, augmentation, loss functions, evaluation metrics, and model debugging.</div></li><li><div>Experience with common detection metrics such as <strong>mAP, </strong><strong>precision</strong><strong>/recall, </strong><strong>false positive</strong><strong>/</strong><strong>false negative</strong><strong> analysis</strong>, and class-level performance breakdown.</div></li><li><div>Strong data analysis and problem-solving skills.</div></li><li><div>Ability to work cross-functionally with model, data, infrastructure, and deployment teams.</div></li></ul>Preferred Qualifications<ul><li><div>Experience in <strong>autonomous driving, </strong><strong>ADAS</strong><strong>, robotics, or safety-critical perception systems</strong>.</div></li><li><div>Experience with <strong>traffic sign recognition</strong><strong>, </strong><strong>traffic light</strong><strong> recognition, road object detection, or small-object detection</strong>.</div></li><li><div>Familiarity with long-tail scenario mining, hard negative mining, class imbalance handling, and dataset curation.</div></li><li><div>Experience with <strong>ONNX, TensorRT, model quantization, C++ inference pipelines, </strong><strong>CUDA</strong><strong>, or edge deployment</strong>.</div></li><li><div>Experience debugging training-to-deployment consistency issues, including preprocessing mismatch, postprocessing mismatch, quantization accuracy drop, or runtime performance bottlenecks.</div></li><li><div>Familiarity with large-scale data pipelines, scenario tagging, or automated data mining workflows.</div></li><li><div>Strong engineering discipline in experiment tracking, reproducibility, regression testing, and model version management.</div></li></ul>What Success Looks Like<div>A successful engineer in this role will:</div><ul><li><div>Improve TSR detection performance across both common and long-tail traffic sign scenarios.</div></li><li><div>Build reliable data and evaluation workflows to support fast model iteration.</div></li><li><div>Identify and prioritize high-impact failure modes through scenario analysis and data mining.</div></li><li><div>Deliver deployable TSR models with strong accuracy, latency, and robust tradeoffs.</div></li><li><div>Help establish a scalable data-model-evaluation-deployment loop for production TSR development.</div></li></ul>Why Join Us<ul><li><div>Work on production of autonomous driving perception systems with real-world impact.</div></li><li><div>Own an important perception task that directly affects driving safety, rule understanding, and product quality.</div></li><li><div>Collaborate with strong teams across model development, data, deployment, and vehicle platforms.</div></li><li><div>Gain hands-on experience across the full model lifecycle: from data and training to evaluation, optimization, quantization, and onboard deployment.</div></li></ul><div> </div><div><strong>What do we provide</strong></div><ul><li><div>A fun, supportive and engaging environment.</div></li><li><div>Infrastructures and computational resources to support your work.</div></li><li><div>Opportunity to work on cutting edge technologies with the top talents in the field.</div></li><li><div>Opportunity to make a significant impact on the transportation revolution by the means of advancing autonomous driving.</div></li><li><div>Competitive compensation package.</div></li><li><div>Snacks, lunches, dinners, and fun activities.</div></li></ul><div> </div><div>The base salary range for this full-time position is $215,280 - $364,320, in addition to bonus, equity and benefits. Our salary ranges are determined by role, level, and location. The range displayed on each job posting reflects the minimum and maximum target for new hire salaries for the position across all US locations. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training.</div><div> </div><div>We are an Equal Opportunity Employer. It is our policy to provide equal employment opportunities to all qualified persons without regard to race, age, color, sex, sexual orientation, religion, national origin, disability, veteran status or marital status or any other prescribed category set forth in federal or state regulations.</div></div></div></div>

<p>XPENG is a leading tech company that designs, develops, manufactures, and markets intelligent mobility solutions. We explore the diversity of mobility including electric vehicles (EVs), electric vertical take-off and landing (eVTOL) aircraft, and robotics. We focus on creating a future of mobility that uses thoughtful and empathetic intelligence to improve the driving experience. XPENG is committed to in-house R&amp;D, with almost 40% of our employees working in R&amp;D-related areas helping to develop our expanding product portfolio. The Company has created a full-stack Advanced Driver Assistance System (XPILOT), as well as an intelligent operating system (Xmart OS) for an enhanced in-car experience. XPENG has also developed core vehicle systems for enhanced driving capabilities, including powertrains and advanced electronic architecture. XPENG is headquartered in Guangzhou, China with multi-regional offices in Beijing, Shanghai, Shenzhen, Silicon Valley, and San Diego. In 2021, the Company established its European headquarters in Amsterdam, along with other dedicated offices in Copenhagen, Munich, Oslo, and Stockholm. XPENG's EVs are manufactured at the fully-owned plant located in Zhaoqing, China. To further expand our production capacity, two new self-owned intelligent EV manufacturing bases in Guangzhou and Wuhan are under construction now.</p>

Staff Machine Learning Engineer

About the Job

About the Company

Xpeng Motors

Similar Jobs

Senior Machine Learning Engineer - Foundation Model

Senior Machine Learning Engineer - Foundation Model

Senior/Staff Machine Learning Engineer, Planning

Senior/Staff Machine Learning Engineer, Planning

Staff Machine Learning Engineer - AI Foundation

Staff Machine Learning Engineer - AI Foundation

Staff Machine Learning Engineer

Staff Machine Learning Engineer

Lead Machine Learning Engineer

Lead Machine Learning Engineer

Lead ML Engineer - Mapping

Lead ML Engineer - Mapping

Lead Machine Learning Engineer

Lead Machine Learning Engineer

Senior ML Engineer - Mapping

Senior ML Engineer - Mapping

Lead ML/Perception Engineer

Lead ML/Perception Engineer

Staff Deep Learning Engineer

Staff Deep Learning Engineer