Help & Supportcareers@gravityer.com
AI/ML Engineer @ Appinventiv | Former AI Project Intern @ IBM | Research Scholar | Data Science Enthusiast | Computer Vision | Problem Solving | Generative AI
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Learning and developing skills for a professional carrer
UPES
Bachelor of Technology - BTech (Hons.), Computer Science
June 1, 2020 – August 1, 2024
Ambition classes
12th class, non medical
January 1, 2018 – January 1, 2020
Appinventiv
AI/ML Engineer
November 1, 2024 – Present
Noida, Uttar Pradesh, India · Hybrid
Appinventiv
Data Analyst Trainee
May 1, 2024 – November 1, 2024
Noida, Uttar Pradesh, India · Hybrid
IBM
Artificial Intelligence Intern
June 1, 2023 – August 1, 2023
Remote
UPES
Research Scholar
May 1, 2023 – August 1, 2023
Dehradun, Uttarakhand, India · Hybrid
OPEN Community
Student Developer
February 1, 2022 – September 1, 2022
Dehradun, Uttarakhand, India · On-site
My Captain
Campus Ambassador
November 1, 2020 – December 1, 2020
Work from Home
A Deep Learning Approach for Ship Detection & Localization using Satellite Imagery
February 1, 2023 – April 1, 2023
Ship detection and localization is a crucial task for various maritime applications, including vessel traffic management, maritime security, and environmental monitoring. In recent years, there has been a growing interest in using satellite imagery for ship detection and localization due to its wide coverage, high resolution, and ability to capture information in different spectral bands. However, manual analysis of large volumes of satellite imagery is time-consuming and requires significant human effort, making it impractical for real-time applications. To address this challenge, deep learning techniques have been applied to satellite imagery for ship detection and localization. Deep learning has shown remarkable success in various computer vision tasks, including object detection, classification, and segmentation. By using deep learning techniques, researchers have been able to develop automated ship detection and localization systems that can process large volumes of satellite imagery in real-time, making it feasible for applications that require quick response times. This approach typically involves training a deep neural network on a large dataset of annotated satellite images to learn the features that are indicative of ships. The trained network can then be used to detect and localize ships in new satellite images. This approach has shown promising results in several studies and has the potential to revolutionize the way ship detection and localization are performed. In this context, this paper proposes a deep learning approach for ship detection and localization using satellite imagery. The paper presents a detailed analysis of the methodology, including the dataset used, network architecture, and training process. Additionally, the paper evaluates the performance of the proposed approach using various metrics and compares it to other state-of-the-art techniques.
Image object classification using CNN
September 1, 2022 – November 1, 2022
Image Classification is a major aspect in the new era of the developing technological world especially in the digital content identification, pictorial object classification and the computer vision sector of Artificial Intelligence and Machine Learning. Image classification is primarily used for the detection and recognition of every facet of an image based on the dataset that is provided by the user. The detection and the recognition is mainly focused on which type of algorithm we are using for the particular model. The main purpose of this project is to implement the concept of the Deep Learning algorithm primarily Convolutional Neural Network (CNN). The performance of our neural network model is evaluated on the basis of quality metrics known as Mean Square Error (MSE) and the classification accuracy that we would get by training and testing our data numerous times. Result analysis or the final output of the model explains the desired output required by the user i.e, based on the computational training of the data taken from the dataset used, further using the testing dataset for checking the unbiased estimate of the result and then retraining the model accordingly in order to increase the efficiency and the accuracy of the existing prototype model. Lastly ,we will validate the processed data in order to optimise the model parameters considering the final MSE calculations of our model .Hence, we can easily identify the contents in the given image ranging from basic recognition to advanced or tricky recognition as per the dataset used for the training of the model.. Python Programming language used
SQL Basic
HackerRank
June 23, 2026 – Present
Microsoft AI Classroom Series
Microsoft
June 23, 2026 – Present
Introduction to AI
IBM
June 23, 2026 – Present
Technical Support Fundamentals
Grow with Google on Coursera
June 23, 2026 – Present
Hackathon 5.0
Computer Society of India-UPES
June 23, 2026 – Present
Cultural Fit Analysis
The candidate's project diversity is strong within the AI/ML and Computer Vision domains, aligning well with a data-intensive role. The experience as a Data Analyst Trainee and subsequent AI/ML Engineer role at Appinventiv, along with internships at IBM and UPES, show a clear career path towards data analysis and AI. The breadth of skills is concentrated in AI/ML, deep learning, and data processing, which is suitable for the target role of Data Analyst, especially one with an AI/ML focus. The certifications in SQL and AI further support this alignment. The candidate appears to be a good fit for a data-driven, technically focused culture.
Soft Skills & Operational Fit
The candidate's project descriptions indicate an ability to articulate technical concepts, though the descriptions are quite verbose. The experience as a Campus Ambassador suggests some communication and community-building skills. However, without specific assessment data on communication, logical reasoning, or teamwork, a comprehensive evaluation of soft skills and operational fit is limited. The focus on research and project work suggests an independent worker, but team collaboration skills are not explicitly demonstrated.