Devansh Sharma

AI Researcher

Kharagpur, India4 yrs 4 mos experience
Most Likely To SwitchAI Enabled

Key Highlights

  • Expert in Machine Learning and Deep Learning.
  • Proven track record in Computer Vision projects.
  • Strong background in developing recommendation systems.
Stackforce AI infers this person is a Machine Learning and Computer Vision specialist with experience in B2C applications.

Contact

Skills

Core Skills

Machine LearningDeep LearningArtificial IntelligenceComputer Vision

Other Skills

TensorFlowRecommender SystemsImage ProcessingAlgorithmsData ScienceArtificial Neural NetworksData Analytics

Experience

4 yrs 4 mos
Total Experience
1 yr 5 mos
Average Tenure
2 yrs 3 mos
Current Experience

Zepto

2 roles

Senior Data Scientist

Promoted

Apr 2025Present · 1 yr · Bengaluru, Karnataka, India

Data Scientist

Jan 2024Jun 2025 · 1 yr 5 mos · Bengaluru, Karnataka, India

  • Ads Monetization platform and Ads Search/Recommendation systems

Sharechat

Machine Learning Engineer

May 2022Sep 2023 · 1 yr 4 mos · Bengaluru, Karnataka, India · Remote

TensorFlowRecommender SystemsMachine LearningDeep Learning

Mtx group

Machine Learning Engineer

Jul 2021Apr 2022 · 9 mos · Hyderabad, Telangana, India

TensorFlowMachine Learning

Sync energy

Machine Learning Intern

Jun 2020Aug 2020 · 2 mos · New York, New York, United States

Cinnamon ai

Artificial Intelligence Researcher

Nov 2019Jun 2020 · 7 mos · Greater Tokyo Area

TensorFlowArtificial Intelligence

Auriga it consulting pvt. ltd.

Computer Vision Intern

Jun 2019Jul 2019 · 1 mo · Greater Jaipur Area

  • Parking Lot Automation
  • Developed a python script to detect free spaces in a parking lot and display their position on screen with the help of Computer Vision
  • Implemented Mask-RCNN using it's pretrained weights on COCO dataset to detect vehicles in a frame extracted from a real time video
  • Predicted whether a parking space is empty on the basis of its IoU with detected vehicles and achieved 97% accuracy on a real time video
TensorFlowComputer Vision

Bosch

Data Science Intern

May 2019Jun 2019 · 1 mo · Greater Jaipur Area

  • Automation of Visual Inspection of Impeller using AI
  • Implemented a CNN (VGG16 architecture) to inspect the defect on the chamfered edges of impeller (part of VE Diesel pump)
  • Preprocessed the images using Otsu's thresholding method and achieved an accuracy of 93.89% when tested on 250 images

Titanic app

Data Science Intern

May 2018Jul 2018 · 2 mos · Work From Home

  • Project 1: Used CNN (Inception architecture) to detect the adult content and achieved an accuracy of 95.16% for 1000 test images
  • Project 2: Used CNN (ResNet50 architecture) to detect the type of tumor diagnosis(benign or malignant) with an accuracy of 97.16%
  • Used data augmentation to evenly distribute the data and also to increase size of the dataset which resultantly increased the accuracy

Education

Indian Institute of Technology, Kharagpur

Master of Science - MS — Economics

Jan 2016Jan 2021

Indian Institute of Technology, Kharagpur

Bachelor of Science - BS — Economics

Jan 2016Jan 2021

DAV Public School, Kota

AISSCE

Jan 2014Jan 2016

Stackforce found 100+ more professionals with Machine Learning & Deep Learning

Explore similar profiles based on matching skills and experience