Shubham Shrivastava

About Shubham Shrivastava

Shubham heads AI and machine learning at Kodiak, pushing the limits of generative AI, vision-language models, large foundation models, and spatio-temporal multimodal networks. By fusing camera, lidar, radar, and language signals, his group delivers a holistic, time-consistent 3-D understanding of the world that steers every autonomous decision.He also championed Kodiak’s end-to-end AI flywheel - smart data mining, rapid auto-labeling, focused human refinement, and fleet-scale retraining - so each mile the trucks travel feeds back into sharper perception with minimal engineering overhead.These advances have produced the world’s first fully driverless freight fleet - operating 24/7, hauling paying customers’ freight without a safety driver on board, and proving that autonomy can be both safe and commercially viable at scale.Shubham’s research has appeared at CVPR, ICCV, ECCV, ICRA, and IROS, and he holds more than twenty patents in computer vision and AI. Earlier, he led the perception team at Ford’s autonomous-vehicle program. He holds advanced degrees in Computer Science with a specialization in AI from Stanford University.

Experience

1. Head of Ai

   Kodiak

   Sep 2023 — Present · Mountain View, CA, US

   Building AI-first driverless autonomy at scale. Leading all AI and ML initiatives at Kodiak Robotics, driving both strategic and hands-on development of core technologies for autonomous trucking- Built and deployed GigaFusionNet, a scalable spatio-temporal multimodal model that processes sensor data (cameras, lidars, and radars) across time and space, providing real-time 3D perception to support complex decision-making- Led end-to-end AI architecture development, including foundation models, vision-language models (VLMs), end-to-end driving VLA models, and generative AI solutions, ensuring adaptability and scalability in diverse real-world driving scenarios- Operationalized scalable auto-labeling systems and an automated end-to-end AI flywheel, enabling continuous and autonomous model improvement through data-driven learning loops- Led the deployment of the industry\'s first 24/7 driverless trucks, achieving large-scale autonomous operations with a focus on commercial logistics- Designed and implemented Kodiak’s Modular Cognitive Architecture (MCA) to enable redundancy and fault tolerance, ensuring no single point of failure and supporting high safety and performance standards- Focused on verifiable AI by developing robust, scalable perception and decision-making pipelines that can be continuously validated and improved- Delivered industry-leading innovations that resulted in safer, more reliable autonomous systems, positioning Kodiak as a pioneer in scalable autonomous logistics.

Education

• Udacity

  Deep Reinforcement Learning Nanodegree

• The University of Texas at Arlington

  Master of Science, Electrical Engineering

  2014 — 2016

• Udacity

  Sensor Fusion Nanodegree

• Udacity

  Self-Driving Car Engineer Nanodegree

• Stanford University

  Graduate Program - Computer Science, Artificial Intelligence

  2020 — 2022

• Visvesvaraya Technological University

  Bachelor of Engineering (B.E.), Electronics and Communication Engineering

  2010 — 2014

Skills

• Matlab
• Arm
• Linux
• V2x
• Prescan
• Posix
• Kalman Filter
• I2c
• Qnx Neutrino Rtos
• Debugging
• Bsp
• Keil
• Signal Processing
• Nxp Freescame I.mx6 Solo
• Dspace
• Data Communication
• Embedded Systems
• Embedded C
• Field-Programmable Gate Arrays (Fpga)
• Fpga
• Embedded Software
• Firmware
• Vhdl
• Autonomous Vehicles
• Wireless
• Vector Canalyzer
• Microcontrollers
• Can
• Ieee 802.11p
• Ieee 1609
• Dspace Microautoboxii
• C++
• Image Compression
• Dsrc
• Eb Assist Adtf
• Connected Car
• I.mx 6 Solox
• Assembly Language
• C
• Programming