Applied Computer Vision Engineer – Data Driven Development

About the role

The Video Perception (VIPer) team at Bosch develops perception systems for L2+ Advanced Driver Assistance Systems. As an Applied Computer Vision Engineer you will work on the full lifecycle of the perception stack, from data analysis to production‑ready software, using deep learning techniques on large video datasets.

Key responsibilities

• Develop, train and validate deep‑learning models for object detection, semantic segmentation and lane detection.
• Design and execute experiments, analyse model performance and identify failure modes.
• Process and curate large‑scale unstructured video data to create high‑quality training sets.
• Build and maintain robust MLOps pipelines for data processing, model training and deployment.
• Implement and optimise Python algorithms to meet real‑time embedded system requirements.
• Document and present experimental results, architectural decisions and technical findings to stakeholders.

Required profile

• Bachelor’s degree in Computer Science, Electrical Engineering or a related field.
• 3–8 years of professional experience in computer vision or machine‑learning application development.
• Strong programming skills in Python and solid understanding of object‑oriented concepts.
• Hands‑on experience with PyTorch or TensorFlow 2+.
• Deep knowledge of CNNs, object detection, segmentation and an interest in vision Transformers.
• Proficiency with Git, Docker and Linux development environments.

Required skills

• Python
• PyTorch
• TensorFlow
• Convolutional Neural Networks (CNN)
• Object detection
• Semantic segmentation
• Lane detection
• Vision Transformers
• Git
• Docker
• Linux
• MLOps pipelines
• TensorRT (optional)