About

Sneha Bhattacharya is a highly skilled machine learning engineer with over 3 years of experience in software engineering. She is currently working at Sense as a Machine Learning Engineer, where she is responsible for building robust deep learning models to predict driver impairment, with a focus on generalizability. She is involved in the entire machine learning cycle including data pipeline, modelling, evaluation and SDK integration. Prior to Sense, Sneha worked as a Machine Learning Engineer at Animated Storyboards and as a Machine Learning Scientist at Affectiva. At Affectiva, she built machine learning models to detect the occurrence of yawns and onsets of drowsiness from real-life driving videos using CNNs and LSTM in Keras and TensorFlow backend. She also spearheaded the development of metrics and evaluation methods to characterize and quantify algorithmic bias in face/expression detection models. Additionally, she analyzed driver behaviors over different time periods (day, week, and month) in collaboration with AVT-MIT and trained CycleGAN models from scratch for joint lighting and expression manipulation tasks using face images, to be used for data augmentation. Sneha has a Master's degree in Computer Science from the University of Massachusetts Amherst, where she primarily focused on machine learning and deep learning research. She worked on a paper for pedestrian detection in thermal images, which was published in PBVS 19 at CVPR. Sneha has a wide range of technical skills, including computer vision, machine learning, deep learning, and affective computing. She is proficient in Python, C++, Scikit-learn, Pandas, PyTorch, TensorFlow, NumPy, Keras, Matlab, and SQL. She is also experienced in using Git, AWS, Hadoop, Docker, MongoDB, SQL, and AWS-lambda. Overall, Sneha has 6.53 years of relevant experience in the field of machine learning and software engineering. She is a highly motivated individual with a passion for solving complex problems and building innovative solutions.