Default profile banner
YS

Yash Saxena

@user.2464830

Associate Data Scientist at Celebal Technologies

Jaipur, Rajasthan

https://linkedin.com/in/yashsaxena17/

Celebal TechnologiesSwami Keshwanand Institute of Technology

Yash Saxena is a data scientist with experience in machine learning, deep learning, NLP, and generative AI. He currently works at Celebal Technologies where he has built classification models, NLP pipelines, and LLM-powered chatbots using Azure OpenAI and Databricks. He holds a Bachelor of Technology from Swami Keshwanand Institute of Technology, Jaipur, and holds Microsoft Azure and Databricks certifications.

Experience

Associate Data Scientist

Celebal Technologies

Full-time•May 2022 - Present

Built and deployed ML/DL models using Keras and PySpark on Databricks for donor segmentation. Built lead scoring model using AzureML and CatBoost. Designed and deployed chatbot using Azure OpenAI GPT-3.5 Turbo and GPT-4. Developed document answer retrieval system with SpaCy and BERT. Implemented CI/CD pipelines with MLflow and Databricks Jobs.

Junior Associate Data Scientist

Celebal Technologies

Full-time•Sep 2021 - May 2022

Developed a semantic search system using SpaCy for NLP tasks. Implemented multiple indexing techniques on large document datasets in Azure Blob Storage. Integrated pre-trained BERT models for contextualized word embeddings.

Data Science Intern

TCR Innovation

Full-time•Jun 2021 - Aug 2021

Used pandas, NumPy, Matplotlib, and Seaborn for data cleaning and visualization. Built and evaluated ML models using Scikit-learn for customer churn prediction. Implemented hyperparameter tuning strategies.

Education

Swami Keshwanand Institute of Technology

Bachelor of Technology

Jun 2018 - Jul 2022•Grade: SGPA 8.1/10

Licenses & Certifications

Microsoft Azure Data Scientist Associate

Microsoft

Databricks Machine Learning Professional

Databricks

Generative AI Fundamentals

Databricks

Microsoft Azure Fundamentals

Microsoft

Skills

Machine Learning
Deep Learning
NLP
OpenAI
LLMs
SparkML
Statistical Data Analysis
Prompt Engineering
Generative AI
Python
PySpark
Scikit-learn
TensorFlow
Keras
PyTorch
SpaCy
LightGBM
NLTK
Optuna
Hyperopt
SQL
Azure
Databricks
AWS
MLflow
BERT
Faiss
ElasticSearch
CatBoost