Sourav Kumar

Software Engineer

Gurugram, Haryana, India1 yr 2 mos experience

Key Highlights

Developed machine learning models achieving high accuracy.
Designed innovative inventory tracking systems.
Streamlined software solutions, enhancing team productivity.

Stackforce AI infers this person is a Machine Learning Engineer with a focus on Agritech and Software Development.

Contact

Skills

Core Skills

Machine LearningSoftware Development

Other Skills

AlgorithmsAnylabelingArtificial Neural NetworksC (Programming Language)C++Cascading Style Sheets (CSS)CommunicationComputer ScienceComputer VisionCrystal ReportsDINOv2DartData AnnotationData StructuresDatabases

About

I am an aspiring Machine Learning Engineer with a strong foundation in Python, Data Science, and Software Development. With 1 year of experience as a Software Developer at Ozdocs International, I have honed my skills in Python, Java, Git, and backend development (Node.js, MongoDB, Express.js). Over time, I have developed a deep interest in Machine Learning, AI, and Data Analysis, and have worked on various ML projects involving data preprocessing, model building, and evaluation using libraries like Scikit-learn, TensorFlow, PyTorch, Pandas, and NumPy. My areas of focus include: Supervised and Unsupervised Learning 1 - Model Training and Evaluation 2 - Regression, Classification, and Clustering Algorithms 3 - Data Cleaning and Feature Engineering 4 - Creating Deep Neural Networks I am actively seeking Machine Learning, AI, or Data Science roles where I can contribute my skills in programming, algorithms, and data modeling, and continue to grow as part of a collaborative and innovative team.

Experience

Intello labs

2 roles

Software Engineer

Sep 2025 – Present · 6 mos · Gurugram, Haryana, India · On-site

Software Engineering Trainee

Mar 2025 – Sep 2025 · 6 mos · Gurugram, Haryana, India · On-site

1 - Developed a grain classification system using hybrid features from DINOv2 embeddings + LBP texture + pixel-level darkness, achieving up to 86% accuracy across 4 quality classes (Normal, Black Tip, FM, Potia) using models like MLP, XGBoost, and LightGBM.
2 - Designed and deployed a QR code-based inventory tracking system using Raspberry Pi + FastAPI + Streamlit, supporting real-time scanning, classification (size, layers, color), and live data sync with a centralized server, with active state pinging and modular GPIO control.
3 - Built a modular SQLite database pipeline for edge devices to log image metadata and sync statuses (TBD, syncing, synced), enhancing reliability and auditability in production-grade Raspberry Pi deployments.

FastAPIStreamlitDINOv2MLPXGBoostLightGBM+3

Ozdocs india pvt ltd

Software Developer

Dec 2021 – Aug 2022 · 8 mos · Noida · On-site

1-Developed and implemented scalable software solutions, resulting in a 30% increase in the existing performance.
2-Streamlined and optimized existing codebase, resulting in a 50% reduction in software errors and improved overall efficiency.
3-Maintained and supported existing applications, providing timely resolutions to issues and ensuring continuous functionality, minimizing downtime by 15%.
4-Actively participated in code reviews and knowledge-sharing sessions, contributing to a 10% increase in team productivity.

PythonJavaGitNode.jsMongoDBExpress.js+1