# Abhinav Gupta > Autonomy@Skydio | CMU Robotics Location: San Francisco, California, United States Profile: https://flows.cv/abhinavgupta Hey there! I’m currently at Skydio, working in the deep learning team to expand the autonomous capabilities of the platform. I’m particularly interested in taking learning-based models all the way from model design and optimisation to production, and ensuring strong downstream geometric consistency. Previously, I worked at Mach9 Robotics, where I focused on building scalable perception and mapping systems for autonomy. My work included transformer-based multi-modal models for panoptic segmentation, HD map prediction, and LiDAR-driven geometric feature extraction. I hold an M.S. in Robotic Systems Development from Carnegie Mellon University, where I built a strong foundation across the autonomy stack, with an emphasis on 3D vision, geometric methods, and learning-based perception. At CMU, I worked on problems spanning monocular 3D reconstruction, pose estimation, vision-language grounding, mapping, and robot manipulation, combining classical geometry with modern deep learning. I'm always happy to chat, so feel free to reach out if you want to talk robotics or AI (or share industry gossip)! ## Work Experience ### Autonomy Engineer- Deep Learning @ Skydio Jan 2026 – Present ### Perception Software Engineer @ Mach9 Jan 2024 – Jan 2026 | San Francisco Bay Area ### Machine Learning Engineer Intern @ National Robotics Engineering Center Jan 2023 – Jan 2023 | Pittsburgh, Pennsylvania, United States - Designed a semi-supervised domain adaptation pipeline to improve the 3D detection performance of agricultural robot harvesters in unseen environments - Conducted ML experiments for hyperparameter tuning and model quantization on Xilinx FPGA - Implemented a multi-object tracking-based car occupancy registration approach and demonstrated it on a field robot in a real parking lot ### Computer Vision Researcher | Robot Learning Lab @ The University of Freiburg Jan 2022 – Jan 2022 | Germany - Introduced a novel task of "Pose-aware Panoptic Segmentation" in urban self-driving environments to simultaneously predict 6D instance pose and panoptic segmentation of the scene - Proposed a Panoptic-DeepLab inspired model architecture and a new evaluation metric; Augmented model performance with depth uncertainty estimation and multi-scale semantic feature fusion modules - Polished Pytorch skills by implementing end-to-end model training, testing and hyper-parameter optimization ### Robotics Software Engineer @ Drishti Works Jan 2021 – Jan 2021 | Mumbai, Maharashtra, India - Worked on a novel visual-servoing based navigation for a farm robot which achieved 94.5% coverage of a two-acre farm with less than 2.4 crops missed per row - Contributed to the development of perception stack for an autonomous beach monitoring robot. Finetuned and deployed TensorRT optimized YOLO V3 object detection on a Jetson Xavier NX for real-time application ### Robotics Researcher @ Kharagpur Robosoccer Students Group Jan 2018 – Jan 2020 | Indian Institute of Technology, Kharagpur, India KRSSG is a team of ardent robotics technocrats from the Indian Institute of Technology, Kharagpur working together to build autonomous soccer-playing robots, the Kharagpur Robosoccer Students' Group (KRSSG) marked its inception in August 2009. We build Small Size League (SSL) robots from scratch right from designing CAD models and circuits to perception, planning and controls, we handle everything! I was the technical lead and mentored the team of 20+ members which qualified for the World RoboCup 2020, France. ### Research Intern | Design and Controls @ NCBLab Jan 2020 – Jan 2020 | Edmonton, Alberta, Canada Stroke is the leading cause of upper body paralysis in more than 60% of people. In this work, I conceptualized the design of a 6-DOF adaptable soft arm exoskeleton for rehabilitation and assistance. I gained practical experience by conducting muscle-model simulations and experiments to analyze joint motion using force plates, IMUs and Motion Capture Systems (MCS) ## Education ### Bachelor of Technology - BTech in Mechanical Engineering Indian Institute of Technology, Kharagpur ### Master of Science - MS in Robotic Systems Development Carnegie Mellon University ## Contact & Social - LinkedIn: https://linkedin.com/in/alpha-gupta --- Source: https://flows.cv/abhinavgupta JSON Resume: https://flows.cv/abhinavgupta/resume.json Last updated: 2026-03-29