Computer Vision Engineer

Computer Vision | Generative AI | Automotive Manufacturing | Battery Manufacturing | Industry 4.0| Medical Imaging| Digital Image Processing| Deep LearningKey Responsibilities:Design, implement and test deep learning models across a range of engineering design problems. Use deep knowledge in computer/machine vision techniques to solve manufacturing engineering problems for industry 4.0/smart manufacturing - viz. In-line Weld (Laser, RSW, GMAW) quality detection, Laser weld CO2 leak detection, In-line Paint quality detection, In-line Quality Control of adhesive dispensing systems etc.Apply advanced pattern recognition techniques to images for machine learning applications in engineering simulation. Apply Generative AI to solve battery design and manufacturing problems.Maintain an awareness of the latest deep learning methods and be able to pair the correct methods to a problem description.Work in a multidisciplinary team and collaborate with other teams.Lead the development of new predictive models working with internal stakeholders from gathering requirements to deliveryResearch, design, and develop new machine learning solutions and algorithms. Keep abreast of the latest in this area including explainable AI, Quantum Machine Learning etc.Support advanced analytical and data mining efforts which could include but not limited to clustering, segmentation, logistic and multivariate regression, decision/CART trees, neural networks, time-series analysis, sentiment analysis, Bayesian analysis etc.Lead/support the Method development activity in the area of Active Safety and ADAS virtual simulations using AI/ML concepts and tools. Submit records of invention into organization's patent submission system along with journal/conference paper publications. Required Skills and Experience:Ø Specialization in machine learning/predictive analytics/operations research or other data analytics areasØ Hands on experience with image processing tools and techniques.Ø Experience building Deep Neural Network models using CNNs, GANs, Transformers, Self-Supervised Learning and/or Multi-Task Learning.Ø Experience building different types of architectures like U-Net, Auto-Encoders, Mask R- CNN, Transformers, 3D U-Net and Resnet architecturesØ Experience with camera-based sensor systemsØ Experience with 3D/4D reconstruction of X-Ray, CT-Scan images and defect identification from such images.Ø Experience with 2D, 3D object detection and tracking, gesture recognition, depth estimationØ Track record of driving atleast one ML research project from conception to production.Ø Hands on experience in DOE based optimization tools.Ø Strong programming skills in Python, C++, C#, Matlab Ø Strong problem solving, analytical, and conceptual thinking skills, resourceful and adaptive with the ability to find ways around obstacles to develop solutions.Ø High level of interpersonal skills with a demonstrated ability to work effectively cross-functionally and cross-culturallyØ Demonstrated self-starter who can work independently and deal with ambiguity. Education:Ø Ph.D or MS/MTech in CS/EE/Mech or related branches of engineering from premier institutes like IITs/IISc/NITs etc.  PRB