AI/ML Expert

Role overview

AI/ML Expert at Bosch Global Software Technologies

Research & Development for Driver Modeling : Conduct pioneering research to develop novel algorithms and models specifically tailored for critical driver modeling tasks, including: Domain-Aware Representation Learning: Investigate and develop effective methods for extracting robust, semantically meaningful, and interpretable features from multi-modal sensor data.

This role is pivotal in enhancing the safety, comfort, and personalization of our next-generation automotive interior monitoring products.

Responsibilities

• This includes leveraging geometric, behavioral cues, alongside modern representation learning techniques, to capture essential aspects of driver state actions and behavior.
• Driver State and Behavior Analysis: Advanced detection of driver attributes like Distraction, Drowsiness (including micro-sleeps), Sleep onset, and emotional states.
• This involves developing sophisticated models to understand and predict complex human behavior, leveraging statistical methods, information theory, and probabilistic approaches.
• Driver Intent and Activity Recognition : Interpreting driver intent, head pose, gaze tracking, eye- gaze estimation, and recognizing specific activities (e.g., phone usage, eating, interacting with vehicle controls). 3D Interior Scene and Driver Interaction Understanding : Interpreting the driver's environment and their interactions within the vehicle cabin for a holistic understanding.
• Algorithm Implementation & Optimization for Automotive: Design, train, and optimize deep learning models (e.g., CNNs, Transformers, Recurrent Neural Networks) and advanced traditional computer vision algorithms for core perception tasks central to driver modeling, utilizing multi-modal sensor data commonly found in automotive environments (e.g., RGB, IR, Depth cameras).
• Focus on computational efficiency and real-time performance suitable for embedded systems.
• Automotive-Grade Data & Pipelines: Devise comprehensive data collection, annotation, and augmentation strategies specifically for diverse driver populations and real-world driving scenarios.
• Manage and curate large-scale, high-quality automotive datasets for model training, validation, and benchmarking.
• Stay abreast of the latest advancements in AI/ML and computer vision research relevant to driver modeling, contributing to the company's IP through patents or publications.
• Required Qualifications & Skills:

Required qualifications

• Master's or PhD in AI/ML, Computer Science, Electrical Engineering, or a related technical field, or equivalent practical experience with a strong focus on computer vision for automotive applications.
• Technical Proficiency : Strong programming skills in Python and C++, with experience in optimizing code for performance.
• ML/CV Expertise : Deep understanding of computer vision fundamentals, image processing, and proven experience with both traditional computer vision techniques (e.g., feature descriptors, geometric vision, optical flow) and machine learning/deep learning frameworks (such as PyTorch and TensorFlow).
• Ability to intelligently combine these approaches for robust solutions.
• Hands-on Driver Modeling
• Demonstrable hands-on experience building, training, and deploying perception systems specifically for driver modeling, human-centric AI, or related automotive interior sensing applications.
• This includes academic projects, industry experience, or contributions to open-source initiatives focused on driver understanding.
• Core Concepts : Solid grasp of mathematical, statistical, and information theory concepts, including linear algebra, calculus, probability theory, stochastic processes, and concepts like entropy.
• This theoretical foundation is essential for advanced algorithm development, particularly in modeling complex human behavior and uncertainty.
• Problem-Solving : Excellent analytical and problem-solving skills, with the ability to tackle complex, novel challenges inherent in developing safety-critical automotive systems.

Preferred qualifications and skills

• Publications: Publications at top-tier AI/CV conferences (e.g., CVPR, ICCV, ECCV, NeurIPS) related to human pose estimation, facial analysis, gaze tracking, activity recognition, feature engineering for behavioral cues, or driver behavior analysis.
• Multi-modal Sensor Fusion: Experience with multi-modal sensor fusion techniques (e.g., camera, RGB/IR, radar) for robust perception in automotive environments.
• Embedded Systems/Optimization: Experience with model compression, quantization, and deployment on embedded automotive hardware or resource-constrained devices.
• Real-time Systems: Experience designing and optimizing algorithms for real-time performance in production environments.
• B-Tech / M.Tech 15+

Employment details

• Location: Coimbatore [India]

About the employer

• Bosch Global Software Technologies Private Limited is a 100% owned subsidiary of Robert Bosch GmbH, one of the world's leading global supplier of technology and services, offering end-to-end Engineering, IT and Business Solutions.

Additional role details

• With over 27,000+ associates, it’s the largest software development center of Bosch, outside Germany, indicating that it is the Technology Powerhouse of Bosch in India with a global footprint and presence in the US, Europe and the Asia Pacific region.
• We are seeking a highly skilled and motivated AI/ML Researcher to design, develop, and deploy cutting-edge computer vision systems specifically for driver modeling applications.
• The ideal candidate will combine strong research skills with practical engineering experience to translate innovation into production-ready, robust, and reliable driver modeling solutions for the automotive industry.