Ruchi Kumari

Software Engineer

Delhi, India1 yr 7 mos experience

Most Likely To SwitchAI ML Practitioner

Key Highlights

Developed a high-accuracy cuisine classification model.
Streamlined data processing for emotional perception analysis.
Active participant in tech initiatives and collaboration.

Stackforce AI infers this person is a Machine Learning and Research professional with a focus on data-driven solutions.

Contact

Skills

Core Skills

Machine LearningData AnalysisResearch Methodology

Other Skills

AirtableAlgorithmsAlternative SolutionsAnalytical SkillsApplication Programming Interfaces (API)Attention to DetailAutomationBatch ProcessingBootstrap (Framework)C (Programming Language)C++Capacity PlanningCascading Style Sheets (CSS)Classification AlgorithmsCommunication

About

Currently a Software Engineer Intern at Amazon, pursuing a Bachelor of Technology in Electrical, Electronics, and Communications Engineering at Indraprastha Institute of Information Technology, Delhi, expected to graduate in May 2025. Contributed to projects involving data visualization and conversational AI, showcasing a practical application of technical skills. Also serves as a Teaching Assistant at Scaler and actively participates in tech initiatives, reflecting a passion for collaboration and learning.

Experience

1 yr 7 mos

Total Experience

6 mos

Average Tenure

11 mos

Current Experience

Payglocal

Software Developer

Jul 2025 – Present · 11 mos · Bengaluru, Karnataka, India · On-site

Amazon

Software Engineer Intern

Jan 2025 – Jun 2025 · 5 mos · On-site

Complex systems laboratory

Undergraduate Researcher

May 2024 – Aug 2024 · 3 mos · New Delhi, Delhi, India · On-site

Design and implementation of a cuisine classification model capable of identifying over 50 unique cuisines based on ingredient profiles, leveraging a dataset of 10,000+ global recipes.
Used various classification algorithms including Logistic Regression, Random Forest, XGBoost, and Support Vector Machines (SVM), optimizing through cross-validation to achieve an overall accuracy of 92% and a precision score of 90%
Implemented hyperparameter tuning using Grid Search and Random Search methodologies, optimizing the Random Forest model’s performance by reducing the classification error by 15%, thus increasing recall on underrepresented cuisine categories.

Classification AlgorithmsLogistic RegressionRandom ForestXGBoostSupport Vector Machines (SVM)Hyperparameter Tuning+4

Visual cognition lab iiitd

Undergraduate Researcher

Aug 2023 – May 2024 · 9 mos · Delhi, India · On-site

Developed custom Python scripts for preprocessing behavioral and pupil data, including filtering, epoching, and baseline correction.
Employed psychometric curve fitting and pupil diameter analysis to quantify emotional perception accuracy and pupil response dynamics.
Designed a controlled experiment with varying noise levels to investigate the relationship between emotional face perception and pupil dynamics.
Achieved streamlined data processing pipelines, enabling efficient extraction of meaningful insights from complex EEG and eye-tracker recordings this improved the performance by 20-30% compared to traditional experimental setups

PythonData ProcessingPsychometric Curve FittingPupil Diameter AnalysisEEG Data AnalysisData Analysis+1