Available to hire
Hi, I’m Yash Modi, a Data Scientist specializing in AI and Machine Learning with hands-on experience in large language models, natural language processing, and RAG pipelines. I enjoy transforming complex datasets into actionable insights and deploying machine learning models that make a real impact, especially in healthcare and enterprise AI systems.
I have a strong background in Python, AWS, and Hugging Face, and I love working in Agile teams to develop scalable AI pipelines and improve user experiences. Let’s connect if you want to discuss innovative AI solutions or machine learning projects!
Skills
Experience Level
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Language
English
Fluent
Work Experience
AI Architect & Software Engineer at AGIL F(X), PHILADELPHIA, PA
August 1, 2024 - PresentDesigned end-to-end modular AI pipelines using LangChain and LangGraph, enabling multi-agent orchestration, workflow automation, and scalable RAG systems. Implemented hybrid search with Pinecone, boosting retrieval precision by 35% and reducing API response time by 20%. Developed reusable React Split components with MUI DataGridPro and Storybook, improving developer productivity and UI customization speed by 35%. Refactored data tables to enhance frontend performance by 20%. Integrated Cypress test suites, increasing test coverage by 40% and ensuring pipeline stability.
Data Scientist (AI/ML Focus) at CVS HEALTH, USA
May 31, 2024 - July 18, 2025Fine-tuned BioBERT and ClinicalBERT models on medical claims data, boosting F1-score by 18% in clinical NLP classification. Built LLM-based summarization pipelines for patient EMR, improving doctor response time by 25%. Automated anomaly detection in medication patterns, reducing manual reviews by 40%. Developed data pipelines with Python, SQL, and AWS Lambda transforming clinical text into structured features. Collaborated in Agile teams to deploy HIPAA-compliant AI models in SageMaker.
Data Scientist at NEXOVA, INDIA
July 31, 2022 - July 18, 2025Developed predictive models with XGBoost and Random Forest to forecast customer churn and cross-sell potential, improving retention campaign ROI by 22%. Engineered NLP pipelines for customer support ticket classification and summarization. Deployed ARIMA and Prophet time-series forecasting models for sales and inventory planning, reducing stock-outs by 15%. Designed real-time dashboards in Power BI to visualize insights, KPIs, and forecasts. Created automated ETL workflows with Airflow and SQL, cutting data latency and manual processing.
Education
Master in Computer Science at The University of Texas - Arlington
August 1, 2022 - May 31, 2024Bachelor in Computer Engineering at Gujarat Technological University
June 1, 2018 - July 31, 2022Qualifications
AWS Certified Cloud Practitioner
January 11, 2030 - July 18, 2025Deep Learning Specialization
January 11, 2030 - July 18, 2025Introduction to LangGraph and LangChain
January 11, 2030 - July 18, 2025Machine Learning - Coursera
January 11, 2030 - July 18, 2025Industry Experience
Healthcare, Software & Internet, Life Sciences, Financial Services, Transportation & Logistics
Skills
Experience Level
Expert
Expert
Expert
Expert
Expert
Expert
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Intermediate
Hire a Data Scientist
We have the best data scientist experts on Twine. Hire a data scientist in New York today.