# Isht Dwivedi

> Engineering @ Applied Intuition

Location: San Jose, California, United States
Profile: https://flows.cv/isht

I work on computer vision problems related to autonomous vehicles. 

Please visit my Google Scholar for a list of my publications.

Google scholar profile -> https://scholar.google.com/citations?hl=en&user=aBMxNDIAAAAJ

## Work Experience
### Software Engineer - Machine Learning and Perception @ Applied Intuition
Jan 2025 – Present
Perception and Scene Understanding

### Senior Research Engineer @ Honda Research Institute USA, Inc.
Jan 2024 – Jan 2025
- Created in-house HD map dataset for estimating lane connectivity (at intersections) using camera only data
- Road Condition Monitoring Project for detecting and geo-tagging damaged road infrastructure.

### Research Engineer 2 @ Honda Research Institute USA, Inc.
Jan 2021 – Jan 2024
- Road scene understanding with emphasis on unstructured events like construction zone

### Research Engineer @ Honda Research Institute USA, Inc.
Jan 2019 – Jan 2021 | Mountain View
Trajectory prediction for road agents and road scene video classification

### Graduate Teaching Assistant @ Columbia University in the City of New York
Jan 2018 – Jan 2018 | Greater New York City Area
Spring - Deep Learning
Responsibilities include creating and grading homeworks, holding office hours

Fall - Deep Learning
Awarded CA Fellowship with tuition waiver for excelling as a Course Assistant.

### Research Intern @ Honda Research Institute USA, Inc.
Jan 2018 – Jan 2018 | Mountain View, CA
Working on deep-learning based vision aspects of autonomous driving cars.
Our paper submitted to the International Conference on Robotics and Automation (ICRA) 2019 during the internship has been accepted!

### Research Associate @ Indian Institute of Science (IISc)
Jan 2016 – Jan 2017 | Video Analytics Lab, Bangalore
•	Developed a fully automatic Hierarchical CNN used for semantic segmentation of hand drawn 
        sketches with pose estimation as auxiliary task.
•	Fully automatic, works without class information on over 11 classes including cat, car, bird, bicycle and airplane.
•	Sketches not required for training: Sketchification process used for converting natural photos to 
        sketch like images.
•	This work was published as a full research paper at ACM Multimedia 2017. It is also available on arxiv with the title "SketchParse: Towards Rich Descriptions For Poorly Drawn Sketches Using Multi-Task Deep Networks".

### Summer Intern @ Ecole Polytechnique
Jan 2015 – Jan 2015 | Laboratoire Leprince-Ringuet, Paris Area, France
•	High energy particles decay in particle detector generating new particles in a graph like pattern. Designed and implemented an approach to reconstruct vertices of this graph.
•	Written in C++, using PCA and Arbor Particle Flow Algorithm, experiments done on Monte Carlo simulations.

### Summer Intern @ Hanyang University
Jan 2014 – Jan 2014 | Computational Vision and Fuzzy Systems Lab, Ansan, Gyeonggi-do, Korea
•	Developed an input method service (keyboard) for the Korean language in android, which offers word predictions while typing.
•	Implemented interval type 2 Fuzzy C Means algorithm.


## Education
### Master's degree in Computer Science
Columbia University

### Bachelor of Technology (B.Tech.) in Major in Electrical and Electronics Engineering, Minor in Computer Science and Engineering
Indian Institute of Technology, Guwahati


## Contact & Social
- LinkedIn: https://linkedin.com/in/isht7
- GitHub: https://www.github.com/isht7

---
Source: https://flows.cv/isht
JSON Resume: https://flows.cv/isht/resume.json
Last updated: 2026-04-11