HOLA!

I'm Jaya Sai
Kishore

I focus on transforming data and models into useful, deployable solutions. I’m particularly interested in model development, evaluation and scaling techniques that improve performance and reliability.

View Projects Download CV

About

I am a Machine Learning Engineer with hands-on experience in developing, evaluating, and deploying machine learning and deep learning models in production environments. My work focuses on transforming data into scalable, reliable solutions that support real-world decision-making.

I’m currently pursuing a Master’s in Data Science & AI and have worked across applied machine learning, NLP, computer vision, and production-grade data systems. My experience spans Python, TensorFlow, PyTorch, CI/CD automation, containerized deployments, MLOps practices, and modern LLM/RAG workflows. I’m particularly interested in structured experimentation, model evaluation, and building end-to-end ML pipelines that scale.

Profile: Data Science & AI
Interests: ML systems, automation, MLOps
Location: Nice, France

Languages: English, French
Skills: Python, SQL, Machine Learning, Deep Learning, TensorFlow, PyTorch, CI/CD, Docker
Web: FastAPI, Flask, Streamlit

LinkedIn GitHub

Resume

I’ve worked across software engineering and data science, contributing to ML workflows, automation, and experimentation. Below is a quick overview of my experience and education.

Experience

Machine Learning Engineer — Starlite Infotech Ltd.

Jan 2023 – Sept 2024

Designed, trained, and deployed production-grade machine learning and NLP systems, focusing on model performance, scalability, and reliable delivery.

Built end-to-end ML and deep learning pipelines including data preprocessing, feature engineering, model training, and evaluation.
Developed NLP models for classification, similarity search, and text analytics using TensorFlow and PyTorch.
Optimized models through hyperparameter tuning, validation strategies, and error analysis.
Deployed models as REST APIs using FastAPI and Docker, enabling real-time inference in production systems.
Worked with embeddings, experiment tracking, and reproducible workflows aligned with MLOps best practices.

Sr. Software Engineer — Capgemini Technologies

Dec 2021 – Dec 2022

Supported ML-driven and data-intensive features within production-grade systems.

Supported data pipelines used for analytics and machine learning workflows.
Collaborated with data scientists to operationalize preprocessing and feature generation logic.
Worked on containerized services and CI/CD pipelines to enable consistent and reliable deployments.
Assisted with monitoring, logging, and debugging of data-driven services in production.

Data Science Intern — Digital Lync

Jun 2019 – Apr 2020

Supported end-to-end ML experiments from datasets to model evaluation.

Prepared datasets through cleaning, normalization, and feature extraction.
Trained and evaluated classical ML models using metrics such as accuracy, precision, recall, and AUC.
Performed exploratory data analysis and error analysis to guide model improvements.
Documented experiments and results to support iterative model development.

Education

Master's in Data Science & Artificial Intelligence

DataScienceTech Institute • 2024 – 2026 • Sophia Antipolis, France

Advanced coursework in machine learning, deep learning, data engineering and MLOps.
Hands-on projects in forecasting, computer vision and LLM/RAG-based applications.
Focus on designing end-to-end ML workflows, from experimentation to reliable delivery.

Bachelor's in Electronics and Communication Engineering

Gudlavalleru Engineering College • 2015 – 2019 • Andhra Pradesh, India

Built strong foundations in mathematics, signal processing and communication systems.
Developed core programming, problem-solving and engineering skills.
Academic projects that sparked interest in data-driven systems and ML.

Projects

A few projects that reflect my interest in forecasting, risk prediction, emotion-aware systems and document understanding.

Air Quality Forecasting Platform

Forecasting workflow for air quality in the Côte d’Azur region using public environmental data. Compares time-series models and neural baselines and presents predictions through a dashboard for station-wise analysis.

GitHub ↗

Emotion-Aware Insight Generator

Emotion analysis prototype that extracts facial affect features and transforms them into context-aware insights. Combines computer vision and text interpretation models, supported by validation and interpretability checks to refine predictions and improve reliability.

GitHub ↗

PDF Understanding & AI Summarization

Retrieval-assisted summarization system that breaks long PDFs into chunks, retrieves useful context and generates concise interpretations using a language model.

GitHub ↗

Machine Learning for Diabetes Risk Prediction

End-to-end diabetes risk prediction system built on a 15k-row clinical dataset. Designed a robust data-cleaning and feature-engineering pipeline, evaluated multiple models and selected XGBoost, achieving 96% accuracy and a 0.993 AUC on the test set. Deployed a real-time FastAPI web app for instant predictions from user health metrics.

GitHub ↗