Arjun (Megharjun) Nandakumar
Co-Founder / CTO @ Scout Robotics
About
I am a passionate Computer Vision and Machine Learning Engineer with a strong background in robotics, deep learning, and AI-driven perception systems. With a Master’s degree in Robotics from the University of Pennsylvania and hands-on experience in industry and research, I specialize in designing and optimizing computer vision models for real-time applications. Currently, I work as a Computer Vision Engineer at AirWorks Inc., where I develop cutting-edge 3D object detection and semantic segmentation pipelines for large-scale geospatial data. My expertise includes optimizing deep learning models for efficiency, implementing custom CUDA kernels for parallelized training, and enhancing model architectures for real-world applications. Previously, I contributed to the development of machine learning solutions at Tortuga AgTech, where I implemented real-time vision-based models to improve robotic harvesting efficiency. I have also worked extensively in research, including at the GRASP Lab and Vijay Kumar Labs, where I developed innovative 3D perception models and deployed deep learning pipelines on edge devices. Beyond my professional experience, I am deeply involved in developing autonomous systems, real-time object detection, and motion planning algorithms. I have led multiple projects in 3D reconstruction, SLAM, and autonomous navigation, leveraging my skills in Python, C++, TensorFlow, PyTorch, ROS2, and NVIDIA GPU optimization. Driven by a passion for AI and robotics, I continuously seek to push the boundaries of machine learning in real-world applications.
United States
Philadelphia
Information Technology & Services
C (Programming Language), Leadership, Research, Matlab, Public Speaking, Python (Programming Language), Project Management, Data Analysis, C++
Experience
Co-Founder / CTO
Scout Robotics
Computer Vision Engineer
AirWorks
Boston, Massachusetts, United States
M.S.E in Robotics
University of Pennsylvania
Philadelphia, Pennsylvania, United States
Graduate Teaching Assistant
University of Pennsylvania
Philadelphia, Pennsylvania, United States
Worked as a graduate teaching assistant for the course ESE 546: Principles of Deep Learning. Topics include: linear regression, backpropagation, neural architectures (convolutions, recurrent networks, attention modules), loss functions, data augmentation, regularization techniques, accelerated variants of SGD, Variational inference, and generative models.
Graduate Teaching Assistant
University of Pennsylvania
Philadelphia, Pennsylvania, United States
Worked as a graduate teaching assistant for the course ESE650: Learning in Robotics. : Topics include Controls, Path Planning, Perception, Probabilistic filtering, and Reinforcement learning.
Computer vision/Machine learning Engineer
Tortuga AgTech
Denver, Colorado, United States
Implemented a real-time computer-vision-based size measurement model using an NVIDIA GPU to measure the height and weight of strawberries before they are picked by a robot. Developed robust metrics and active model evaluation pipelines to continuously assess and optimize the model’s performance, ensuring high accuracy and efficiency in the automated process.
Machine Learning Engineer
iMov MotionTech
Bengaluru Area, India
Working on developing multi-node wireless technology with an integrated Cloud interface and Smart FES technology. Developed Gait systems for the measurement, analysis, and control of human movement. Currently, we are working on developing advanced medical-grade rehabilitation devices for the treatment and assessment of movement disorders. Represented the Team at Gopalakrishna Despandhe foundation Cohort, IIT Madras. Was selected to represent the start-up at the M2D2 challenge and workshop.
Lead Technology Engineer
EWar Games
Bengaluru Area, India
Guiding and working with the start-up for the development of the first MVP. System algorithm design and hardware architecture . Real-time Analytics to improve Cricket batsmen performance. IOT architecture IMU Signal processing algorithms Sequence learning algorithms
Research Associate
Indian Institute of Technology, Madras
Chennai Area, India
Wireless body area Networks: Developing and implementing wireless protocols for multi-node communication with efficient throughput and data rates. Biomechanical models: Developing RNN and LSTM models and Event Detection models for automation.
Research Associate
Department of Science and Technology
Bengaluru Area, India
Research Associate for a Department of Science and Technology Funded Research Project ”Design and Development of a Low Cost, Portable Gait Motion Analysis System”. SERB(DST ref: SB/S3/EECE/059/2015)
Education
University of Pennsylvania
Arjun (Megharjun) Nandakumar's Contact Information
Phone
Find the Right Leads
Find Verified Contact Data
What LeadContact does well
Find verified emails, phone numbers, and decision-makers with 98% accuracy.
Find Leads
Find the right people by company, role, industry, location, and more.
925M+ professional profiles
Find Emails
Access verified email addresses for your target contacts.
657M+ emails
Find Phone Numbers
Get cross-validated phone data from multiple top sources.
239M+ phone numbers
More Accurate. Lower Cost.
Find contact data in 1 tool with 98% accuracy
LeadContact integrates leading enrichment tools to deliver more accurate contact data—without paying for each one.
Great conversations start with the right contact.
It’s time to find yours.