3 days ago
Wuppertal, GermanyMid Level
Responsibilities
- Develop, train, evaluate, and optimize machine learning and deep learning models for computer vision tasks such as pose estimation, volumetric modeling, object detection, semantic segmentation, and classification.
- Implement classical and modern computer vision algorithms for feature detection and extraction, depth matching, 3D scene reconstruction, and novel-view generation.
- Build maintainable Python code for ML training pipelines, data processing, visualization, and algorithm prototyping.
- Process point clouds, meshes, and volumetric representations, including registration, transformation, computation, and visualization.
- Perform mesh fitting and geometry-aware model integration within processing pipelines.
- Prototype algorithms, ML models, and geometry-based methods for feasibility evaluation, benchmarking, and customer demonstrations.
- Support data collection campaigns and validate recordings for ML training and evaluation.
- Help productize algorithms by integrating them into automated pipelines and reproducible ML environments.
- Collaborate with R&D engineers, 3D reconstruction specialists, cloud pipeline engineers, and data operations teams.
- Document algorithms, experiments, design decisions, and technical findings.
Requirements
- Master's degree in computer vision, machine learning, robotics, computer science, or a related field.
- Strong experience training and evaluating ML models, preferably for pose estimation, segmentation, object detection, or 3D and volumetric modeling.
- Solid background in classical computer vision, photogrammetry, and multi-view geometry.
- Strong Python programming skills and experience with ML frameworks such as PyTorch or TensorFlow.
- Experience with 3D data formats including point clouds and meshes and with related processing and visualization tools.
- Knowledge of stereo, multi-view, geometric, or learning-based depth estimation algorithms.
- Strong analytical skills and ability to independently contribute to experiments and model improvements.
- Excellent communication skills, teamwork, and willingness to support cross-functional efforts.
- Fluent English.
- Preferred: C++ experience for high-performance algorithmic implementations.
- Preferred: familiarity with novel-view generation, differentiable rendering, neural rendering, or NeRF-style approaches.
- Preferred: understanding of Docker, CI/CD pipelines, and ML workflow automation.
- Preferred: experience with pose estimation datasets, 3D human models, Gaussian splatting, or mesh-based learning.
- Preferred: data collection or real-world ML experimentation experience.
- Preferred: background in signal processing, sensor fusion, or geometry-driven ML techniques.
Benefits
- Attractive compensation package, 30 days of annual leave, and overtime compensation.
- Secure, permanent employment contract with internal career development opportunities in an international environment.
- Internal and external training programs, coaching, and certifications.
- Recognition and rewards for innovation and outstanding performance.
- Highly international and collaborative work environment with industry experts.
- Opportunities to participate in Corporate Social Responsibility initiatives.
- Opportunity to shape future mobility by working with global OEMs and technologies including e-mobility and autonomous driving.
Categories
About Aptiv
Aptiv is a public automotive technology supplier that designs and manufactures vehicle electrical architectures, ADAS/autonomous software, connectivity solutions, and engineered components. It sells integrated hardware-software platforms, wiring and power distribution systems, sensors, and infotainment to global automakers and mobility companies. Headquartered in Dublin, Ireland, Aptiv is listed on the NYSE and operates worldwide across development centers and manufacturing sites.