CV

Senior Engineer, AI/ML Software Engineering

Analog Devices

As a senior Machine learning engineer i developed 3D VIsion and AI solutions for Industrial RObotic safety applications. Developed multiple applications for industry leading hardware like ADTF3175 1MP time of flight device and MAX78002 edge CNN accelerator.

• Awarded 'Top 10 Under 10 Award' as a recognition for being among the top 10 contributors to the organization with under 10 years of experience.
• Awarded Best Paper Award in ITEC2023

Machine Learning Engineer

Analog Devices

As a Machine learning engineer, i worked on developing efficient neural network applications for embedded devices. Led the ADI people counter Algorithm project and worked on various other applications like Human tracking, Facial recognition and detection, Condition based monitoring(CBM),etc.

• Won Skynet 2022 AI Hackathon
• Published in multiple conferences and filed my first patent.
• Nominated as AI Mentor for Anveshan 2021 Fellowship program

Intern - Deeplearning And Computer Vision

Analog Devices

As a part of my internship target i upgraded the ADI people count application to use Deep-Learning convolutional neural networks for more efficient Human detection.

• Awarded full time position in recognition of excellient work.

Masters

Carnegie Mellon University

Robotic Systems Development

• Advanced COmputer Vision
• Reinforcement Learning and Control
• Advanced Deep-Learning

Summer School

Indian Institute Of Science

Computer Science & Automation

• Artificial Intelligence
• Quantum COmputing
• Reverse engineering in SOftware

Bachelors

Visvesvaraya Technological University

Computer Science & Engineering

Twn Young Professionals Under Ten(TYPT) 2022

Analog Devices

Awarded the prestigious Analog Devices India Ten Young Professionals Under Ten Award as a recognition for being among the top ten contributors to the organization with under 10 years of Experience.

Best Paper Award - India Technology Conference(ITEC) 2023

Analog Devices

Won the Best Paper Award W at ADI India Technical Conference 2022.

Winner - Skynet AI Hackathon

ADI GTC 2022

Won the Skynet AI Hackathon Challenge at ADI Global Technical Conference 2022

AI Mentor - Anveshan 2020

Analog Devices India

Elected as AI Mentor to guide a team of Undergrads in ADI’s Annual Fellowship Program 'Anveshan'

2nd Position in IIsc Machine Learning Hackathon

Indian Institute Of Science(IIsc)

Secured 2nd Position in Machine Learning Hackathon Organised by Indian Institute Of Science.

ADI Spot Award

Analog Devices

Awarded multiple ADI Spot Awards and ADI Impact Awards for Excellent Professional Performance.

(PATENT)ARCHITECTURE FOR RUNNING CONVOLUTIONAL NETWORKS ON MEMORY AND MIPS CONSTRAINED EMBEDDED DEVICES

United States Patent and Trademark Office(USPTO)

This Patent describes techniques to perform convolutional neural networks (CNNs) on embedded devices. The techniques include operations comprising: accessing DNN information including definition of layers and weights of the DNN; obtaining cache or memory information for one or more cache or memory levels of the resource constrained embedded device; and configuring the DNN to be loaded onto the one or more cache or memory levels of the resource constrained embedded device based on the cache or memory information and the DNN information.

Enhancing vision capabilities of ADTF3175 using 3D Depth stitching algorithm

Analog Devices India Technical Conference 2023

This Publication explores how we enhanced the capabilities of fixed FOV time of flight cameras using a novel and efficient 3D depth stitching algorithm that can combine the FOV of multiple Time of Flight sensors in a modular fashion to give a conventional Lidar like coverage while running on the edge at speeds of upto 100FPS. This work was done with the industry leading Tof Device ADTF3175D, which also won the CES2023 innovation award for being the industry's first 1 megapixel Depth sensor.

Enabling Smart Building Applications on the Edge Using Artificial Intelligence

IEEE Wintechcon

In the paper we discuss various smart building applications which is achieved using occupancy monitoring with Artificial Intelligence.

3D Hand Gesture Control for Human Robot Interaction

The Analog Devices 3DToF Gesture Recognition package is an ROS (Robot Operating System) solution designed for real-time Hand Gesture Reognition. Leveraging the power of deep learning, this package processes depth images captured by ADI's Time of Flight (ToF) sensor to accurately recognize and publish one of 18 distinct gestures. At the heart of the recognition module is a Convolutional Neural Network (CNN), which ensures the system to operate seamlessly at 5 frames per second (FPS) on the EVAL-ADTF3175D-NXZ platform.

• 3D Perception
• Human Robot Interaction(HRI)

Enhancing Vision Sensor Capabilities with 3D Depth Stitching Algorithm

The rising popularity of time of flight (TOF) cameras in industrial applications, particularly in robotics, is attributed to their exceptional depth computing and infrared (IR) imaging capabilities. Despite these advantages, the inherent complexity of the optical system often constrains the field of view, limiting standalone functionality. This article discusses a 3D image stitching algorithm designed for a supporting host processor, eliminating the need for cloud computation. This algorithm seamlessly combines IR and depth data from multiple TOF cameras in real time, producing a continuous, high quality 3D image with an expanded field of view beyond standalone units. The stitched 3D data enables the application of state-of-the-art deep-learning networks—particularly valuable in mobile robotics applications—to revolutionize the visualization and interaction with the 3D environment.

• 3D Depth Stitching
• CUDA optimization

Safety Bubble detector for Industrial AGVs

The ADI 3DToF Safety Bubble Detector is a ROS (Robot Operating System) package for the Safety Bubble Detection application. The Safety Bubble Detectors are the basic building block of any AGV/AMR. The safety zone is a virtual area around an AGV/AMR. The Safety Bubble Detectors are used to detect the presence of any object inside this zone and prevent the AGV/AMR from colliding on to the object.

• Supports custom safety region configuration
• Achieves multiple Functional Safety(Fusa) Standards.

Floor detector for Industrial AGVs

The ADI 3DToF Floor Detector is a ROS (Robot Operating System) package for the Floor Detection application. The term 'Floor Detection' refers to determining where the floor is in the given image. It is an image segmentation problem in which a given image is divided into floor and non-floor pixels. Floor Detection is an essential component of real-world applications such as Robot Navigation, Autonomous Driving, Augmented reality (AR) applications, and 'Obstacles Detection and Avoidance' for robots and people with inadequate vision. Here is the sample output of ADI 3DToF Floor Detector.

• Fast and robust floor segmentation
• Achieves multiple Functional Safety(Fusa) Standards.

Global Terrorism Vulnerability Forecasting using Deep Learning

Undergrad Thesis - This project includes prediction of vulnerability for various cities and states around the world for specific year intervals. This is done using the Global Terrorism Database maintained by START.inc while creating a separate target feature called 'Vulnerability', which counts the total number of attacks that has been happened in a specific city for a specific year.

• Elected to be among the top 4 best projects from all over India and was featured in IISc’s Official Channel

Chapter Ambassador - Bangalore

AI Saturdays by NUrture.ai

AI Saturdays was a Global Initiative started by a Singapore-based company Nurture.ai where volunteers from over 100 cities around the world hosted free Artificial Intelligence Meetups to help students and professionals get started in their journey of learning AI. This initiative made AI accessible to all. ◦ AI for All: We were operating a Meetup group with over 2000+ active participants across Bangalore. As a part of the program, we organized Fast.ai MOOC learning sessions(Designed by Jeremy Howard), with help from companies like Nvidia and Go-Jek, while also being hosted by co-working spaces across Bangalore.

• Hosted one of the largest meetups in bangalore with 2000+ active participants
• Sponsered by Nvidia, Go-Jek and 91Springboards

Life Member - AI Research

MUST Research Club

MUST Research is India’s one of the most premier AI research club. Together we work towards improving AI technology in India by working on innovative project ideas that can improve human life, helping academia and raising awareness of AI among government Organisations.

• India's Largest group of AI Scientists
• AI For Good

Team Leader - Incoming Global Volunteers

AIESEC

Youth 4 Impact: Led a team that helped connect international volunteers from across the globe, with relevant opportunities with Indian NGO’s for orphans. This was done to promote the ”Quality Education” Sustainable Development Goal(SDG) as defined by the United Nations Council.

• Supported India in meeting the Quality Education United Nations SDG