About the Team
Our team focuses on advancing computer vision and deep learning technologies to enhance perception systems for autonomous systems. We work on state-of-the-art neural network models for LiDAR-to-camera calibration, 3D scene reconstruction, and depth estimation. By combining synthetic data generation, large-scale dataset processing, and rigorous experimentation, we push the boundaries of AI-driven perception. Our work directly contributes to improving the accuracy and reliability of autonomous navigation systems.
About the Role
We are looking for a Research and Development Engineer to design, develop, and optimize neural network-based algorithms for LiDAR-to-camera calibration, 3D scene reconstruction, and depth estimation. You will be responsible for conducting experiments, generating and processing large-scale datasets, and implementing deep learning solutions for real-world applications. Your work will involve using cloud platforms, orchestration tools, and modern machine learning frameworks to create scalable, high-performance solutions. Additionally, you will analyze scientific research, assess the applicability of cutting-edge deep learning techniques, and drive innovation in perception technologies for autonomous systems.
What You'll Do
- Design, develop and support algorithm:
- Neural network LiDAR to camera calibration;
- Calibration boards detection further used in LiDAR to camera calibration;
- Mono-camera 3d-scene neural network reconstruction and depth estimation.
- Formulate and conduct experiments:
- Synthetic image data, including synthetic images and videos generation; train image and video generation neural networks;
- Mono- and multi- camera 3d-scene reconstruction and depth estimation.
- Collect, process and manipulate datasets for large-scale neural network training, including video, image and 3d point cloud data. Use cloud platforms and orchestration tools to design and develop reproducible data collection.
- Analyze and review scientific papers on deep learning algorithms; make company-specific conclusions on applicability and performance of different approaches.
What You'll Need
- Bachelor’s degree in Computer Science.
- Proficiency in Python and its frameworks and libraries: PyTorch, TensorFlow, PySpark, NumPy, SciPy.
- Competency in C++, SQL languages.
- Familiarity with neural networks deployment networks ONNX and TensorRT.
- Familiarity with Argo and AWS Glue, EC2, S3 services.
- Familiarity with self-driving projects' architecture and principles: knowing principles of their work, deployment, data delivery, analytics processes; expertise in servicing and working with self-driving cars and robots.
- At least 3 years of experience in self-driving cars or robots development.
- At least 5 years of professional experience in Software development/engineering or equivalent.
- At least 5 years of experience with Linux, Docker, Kubernetes.
- At least 5 years of neural network related algorithms development, including data collection and processing, training and deployment.
- Knowledge of significant historical and state-of-the-art approaches for imagery and point cloud data.
- Knowledge and experience with basic machine learning algorithms and neural network methods.
- Knowledge and experience with discrete optimization methods.
- Ability to participate in project management activities, set goals and deadlines, collaborate with other teams.
Nice to Have
Candidates are required to be authorized to work in the U.S. The employer is not offering relocation sponsorship, and remote work options are not available.
