I’m a Data Scientist and Product Analyst in the making, currently completing my Master’s in Business Analytics & Artificial Intelligence at The University of Texas at Dallas. With a foundation in data science, machine learning, and product analytics, I thrive on turning data into real-world impact.

My journey spans AI research, full-stack development, and applied analytics, driven by a curiosity to build scalable, intelligent systems that solve real business problems.

• Contributed to COLT and THESAN projects, developing scalable Monte Carlo Radiative Transfer (MCRT) models in Python and C++.
• Simulated early-universe phenomena like galaxy formation and cosmic reionization, sharpening my high-performance computing and simulation skills.

• Designed and deployed a campus chatbot using LangChain, FAISS vector databases, and LLMs, enabling intelligent semantic search on custom PDFs.
• Built for student-facing use cases like admissions and FAQs, demonstrating practical applications of RAG pipelines and prompt engineering.

• Applied XGBoost, Neural Networks, and OLS Regression to predict credit default risks.
• Focused on model interpretability, feature engineering, and comparative model performance across techniques.

• Built NLP models to detect sentiment, emotion, and mental health signals from social media data.
• Fine-tuned transformer models for low-resource environments and improved pipeline efficiency.

• Created a full-stack ML platform for end-to-end data lifecycle management using Flask, Streamlit, and automated preprocessing modules.
• Tackled challenges like model integration, data cleaning automation, and dashboarding.

Actively seeking roles in:

• Product Analytics
• Business/Data Analytics
• Machine Learning & AI Applications

• Languages: Python, SQL, C++, JavaScript
• Frameworks & Tools: PyTorch, Scikit-learn, Hugging Face, TensorFlow, LangChain, FAISS
• Data & ML: Data Cleaning, Feature Engineering, Regression, Classification, Clustering, XGBoost, NLP
• Product & BI: SQL, Tableau, Power BI, A/B Testing, Product Metrics
• Full Stack: Flask, Streamlit, React (Basics), REST APIs
• Cloud & Dev Tools: Azure ML, Git, VS Code, Jupyter

• Passionate black metal guitarist and composer 🎸
• Amateur boxer with a love for discipline, intensity, and personal growth 🥊

• Building intelligent, AI-powered products using NLP and generative models
• Deep-diving into Product Analytics, A/B Testing, and user behavior modeling
• Exploring LLMs, RAG pipelines, and domain-specific chatbots

📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/shobhitpachauri
💻 GitHub: github.com/shobhitpachauri

✨ Let’s connect, collaborate, and build something impactful!