> Markdown version of [/jobs/ext/4627121-software-engineer-motion-prediction](https://www.wearedevelopers.com/jobs/ext/4627121-software-engineer-motion-prediction). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Software Engineer: Motion Prediction - **Company:** Tensor Auto Inc. - **Location:** San Jose, CA, United States - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** Computer Vision, C++ (Programming Language), Nvidia CUDA, Python (Programming Language), Machine Learning, Pytorch, Deep Learning, Build Management, Information Technology, ONNX (Open Neural Network Exchange) Format, TensorRT - **Published:** November 7, 2026 - **Apply:** https://www.juju.com/job/28_25303_e312fe43dc9df15e2d9671a802552f9f ## About the Role * M.Sc. in Computer Science, Electrical Engineering, Mathematics or a related field. * 5+ years of experience with hands-on experience in machine learning projects. * Strong C++ and/or Python programming skills required. * ML Framework Options: CUDA C/ PyTorch/ONNX/TensorRT., * M.Sc. or Ph.D. in computer vision, machine learning, robotics, or a related field. * Extensive experience in deep learning. * Industry research or production experience. * Publications at top-tier conferences, e.g. CVPR, ICCV, ECCV, ICLR, ICML, ICRA, RSS, NeurIPS, AAAI, IJCV, and PAMI. ## Description * Build machine learning models with time-series data for forecasting the future location of vehicles, bikes, pedestrians, including data collection, model design and training and deployment. * Build interactive models to capture the interactive behavior among multiple actors. * Design seamless interface to support both upstream perception team and downstream planning team. * Design and build prediction module performance evaluation system, to quantify system improvements. * Interact with operations team to provide guidance for in-vehicle testing for prediction.