Sakshi Goyal

Results-driven Software Developer with experience at Bertrandt GmbH, specializing in AWS and Docker. Successfully optimized ETL workflows and automated CI/CD pipelines, enhancing development efficiency by 25%. Proficient in Python and C++, with a strong focus on deep learning techniques and agile methodologies, ensuring high-quality software delivery and collaboration.

• Fundamentals of Digital Image and Video Processing, Coursera
• PyTorch for Deep Learning with Python Bootcamp, Udemy
• Generative AI with Large Language Models, Coursera

Monitoring Perception Reliability in Autonomous Driving: Distributional Shift Detection for Estimating the Impact of Input Data on Prediction Accuracy, Franz Hell et al., Computer Science in Cars Symposium, 2021, Ingolstadt, Bavaria, Germany, 9781450391399, 10.1145/3488904.3493382, https://doi.org/10.1145/3488904.3493382

• English
• Hindi

• Unsupervised Deep Networks for Stereo Scene Flow – Deep Learning in Computer Vision Lab
  Developed an unsupervised framework for scene flow estimation using stereo input, enabling simultaneous prediction of depth and optical flow without ground truth supervision.
• Real-Time Proposal-Free Panoptic Segmentation – Master’s Thesis
  Designed and implemented a panoptic segmentation framework in PyTorch, achieving 2× faster inference than state-of-the-art methods while improving segmentation accuracy and efficiency.