Resume
This page is a detailed version of my resume. For a more consolidated one-page version of my resume kindly click on the 'PDF' button on the right side.
General
Name | Shyamsundar Prabhakar Indra |
Title | AI Engineer Intern |
shyampi@terpmail.umd.edu | |
Phone | (240) 398-0284 |
Summary | An aspiring Machine Learning / Computer Vision engineer with solid Mathematical and Programming fundamentals, and a strong inclination towards research based work. |
Education
-
08.2022 - 06.2024 Maryland, USA
M.Eng. in Robotics
University of Maryland, College Park
GPA : 4.00/4.00
- Foundations of Deep Learning (Ongoing)
- Cognitive Robotics (Ongoing)
- 3D Vision
- Robot Programming using C++
- Human Robot Interaction
- Advances in Extended Reality (XR)
- Perception in Robots
- Path Planning in Robots
- Adv. Geometric Computer Vision
- Control of Robotics Systems
- Intro. to Robot Modelling
-
08.2016 - 07.2020 Rajasthan, India
B.Eng.(Hons.) in Mechanical Engineering
BITS Pilani, Pilani campus
GPA : 8.20/10.00
- Machine Learning
- Object Oriented Programming using JAVA
- Intro. to Programming using C
- Intro. to Robotics
- Computer Aided Design (CAD)
- Finite Element Methods (FEM)
- Solid Mechanics
- Fluid Mechanics
- Heat Transfer
- Mechanical Vibrations
- Calculus I, II, III and IV
- Probability and Statistics
- Linear Algebra
Skills
Programming Languages | |
Python (advanced) | |
C/C++ (intermediate) | |
C# (intermediate) | |
MATLAB (beginner) | |
Java (beginner) |
Domain Skills | |
Computer Vision | |
Robotics | |
Machine Learning | |
VR/AR | |
LLMs | |
Software Development | |
Reinforcement Learning | |
CUDA programming |
ML and CV tools | |
PyTorch | |
PyTorch3D | |
TensorFlow | |
Keras | |
Scikit | |
Open3D | |
NumPy | |
OpenCV | |
Pandas |
Development Utilities | |
ROS | |
CUDA Programming | |
Linux | |
Unity | |
Gazebo | |
Blender | |
Docker | |
Git/Github | |
SolidWorks | |
Carla | |
Java Server Pages | |
Google Colab | |
HMTL |
Certificates
Generative AI with Large Language Models | ||
DeepLearning.ai | 05-2024 |
Scaling Workloads Across Multiple GPUs with CUDA C++ by Nvidia | ||
Nvidia Deep Learning Institute | 04-2024 |
Getting Started with Accelerated Computing in CUDA C/C++ by Nvidia | ||
Nvidia Deep Learning Institute | 04-2024 |
Experience
- 06.2023 - 05.2024
Machine Learning Engineer Intern
Renesas Electronics America Inc.
Summary : Specialized in MLOps & developing software for automated AI deployment on Renesas edge devices
- Built a Python edge AI deployment platform with end-to-end ML pipelines catered to time-series & image data from Renesas edge devices’ sensors, enhancing deployment speed by 64% & reducing manual work by 80%, saving over 100 man-hrs/month.
- Integrated ONNX Runtime in the platform, improving model inference speed by 40% & reducing training time by 30%.
- Reduced the edge deployment memory usage size of PyTorch Neural Nets by 52% by implementing Low-Rank Adaptation (LoRA).
- Developed and deployed a Support Vector Machine (SVM) model for voice authentication on a Renesas edge device, using a 500 samples in-house dataset collected manually, achieving 96% accuracy on 100 unseen people from the wild.
- 02.2023 - 06.2023
Graduate Computer Vision Researcher
UMD Vision & Learning Lab
Summary : Conducted cutting-edge research on generative AI models for text-to-3D facial animation
- Performed literature review on 3DGANs, GAN Inversion, & CLIP models for a novel text-to-3D facial animations genAI model.
- Solved an intermediate problem of text based 3DGAN image editing by creating a model integrating EG3D with GAN Inversion for text-based manipulation of latent space using CLIP, trained using the EmotiW (facial emotions) dataset.
- Evaluated the intermediate approach using PSNR, SSIM and CLIP similarity scores to ensure latent space editing success.
- 01.2022 - 08.2022
Robotics Research Intern
Robert Bosch Centre for Cyber Physical Systems - IISc Bangalore
Summary : 3D obstacle detection and lower level controller for WIPRO sponsored L3 autonomous vehicle (AV)
- Developed LiDAR-based 3D object detection model for WIPRO sponsored L3 AV, achieving mAP values of 73% (cars) & 72% (pedestrians) on KITTI3D dataset, by training on Waymo Open dataset & self-curated Carla dataset of 10000 synthetic samples.
- Engineered Control Barrier Functions (CBFs) based lower level controller python software package, which along with the 3D object detection, gave around 92% successful collision avoidance over 50 simulated scenarios in Carla.
- Verified the controller by ROS deployment on a Copernicus UGV, resulting in a published conference paper on the same.
- 01.2021 - 08.2021
Computer Vision Research Intern
International Institute of IT Bangalore
Summary : ROS Perception stack and prototype development for autonomous farm robot
- Curated & annotated around 2000 plant images using Azure Image Labeling tool for YOLO model training using transfer learning.
- Achieved 94.6% accuracy on a publicly available leaf dataset, by training a YOLO leaf detection model for leaf counting, hence enhancing a farm robot’s crop health monitoring capabilities.
- Led a team of 5 junior interns and accelerated completion of farm robot prototype development and ROS perception stack deployment with the leaf detection model on the same, within 22 days.
Achievements
- 2016
All India Rank 1073 in JEE Mains out of 1.2 million candidates
- 2016
Top 0.04 percentile in JEE Advanced, entrance exams to prestigious IITs
Publications
- Webpage
Projects
- Webpage
Extracurriculars
- 07.2023 - Present
Collegiate Badminton Player
University of Maryland (UMD), College Park, USA
Badminton Doubles player representing UMD in collegiate level competitions in the US
- 08.2021 - 06.2022
Volunteer Tutor
Happiee Souls NGO, Chennai, India
Mentored a batch of underprivileged kids taken care of by the NGO who lacked access to basic education, and tutored them in Mathematics, Science and English
- 08.2016 - 05.2020
Collegiate Track and Field Athlete
BITS Pilani, Rajasthan, India
Represented BITS Pilani in several collegiate and open meets. Medal winner in various 100m, 200m, 4x100m and long jump events
- 07.2018 - 04.2019
Student Mechanical Engineer
Pixxel - Student Nanosatellite team, BITS Pilani
Responsible for the simulation of structural and thermal interactions between the space environment and nanosatellites, which were to be launched with the help of Indian Space Research Organization (ISRO) to provide affordable satellite imagery
- 08.2016 - 05.2020
President and Cultural Performer
Pilani Tamil Mandram (PTM), BITS Pilani
Responsible for managing 40+ volunteers and organizing events throughout the year 2017-2018 for PTM, the Tamil Culutral Association of BITS Pilani. Was also an annual dance performer for PTM in BITS Pilani's annual cultural events
Languages
Tamil | |
Native speaker |
English | |
Bilingual proficiency |
Hindi | |
Beginner |
Malayalam | |
Beginner |