Anshuu Shukla

Final-year B.Tech AI/ML student · Aspiring AI/ML Engineer

Kanpur, Uttar Pradesh, India

@anshuu_shukla

LinkedIn GitHub

0 followers

Looking for jobs Looking for internships Open to relocating

🎓 B.Tech in Artificial Intelligence and Machine Learning at Dr. APJ Abdul Kalam Technical University · Graduating 2027

Follow Message

About

Final-year B.Tech student in Artificial Intelligence and Machine Learning with hands-on experience building end-to-end machine learning and generative AI projects. Comfortable working across data pipelines, model training, deployment, and LLM-based applications using modern ML and cloud tools.

Experience

Data Science Intern

IntenQ

Jun 2026 – Present

worked on NLP based Projects , And formed Machine learning Pipelines and created Logs using MLflow like tools

Education

B.Tech

Kanpur Institute of Technology · Dr. APJ Abdul Kalam Technical University

Artificial Intelligence and Machine Learning · 2023 – 2027

Skills

<3 months

SQL RAG NumPy Python Pandas FastAPI PyTorch PySpark XGBoost Streamlit LangChain LangGraph AI Agents TensorFlow OpenAI API LlamaIndex scikit-learn etl pipeline Random Forest Vector Databases Prompt Engineering Feature Engineering Supervised Learning Unsupervised Learning Statistical Inference

Tools / apps / platforms

<3 months

GCP MySQL AWS S3 Docker GitHub Mlflow Tableau PostgreSQL Apache Kafka Microsoft Power BI

Languages

Conversational

Hindi Speak · Read · Write English Speak · Read · Write

Projects

Multi-Source E-Commerce Analytics & BI Platform

SQLAlchemy, PostgreSQL, AWS S3, Power BI, Tableau

Built ETL pipelines to consolidate e-commerce data, applied K-Means and PCA for segmentation, stored processed data in AWS S3, and built BI dashboards.
Generative AI Knowledge Assistant (RAG System)

LangChain, LlamaIndex, OpenAI API, Vector Database

Built a retrieval-augmented generation pipeline to answer questions over a custom document set, using chunking, metadata filtering, and a vector database.
Real-Time E-Commerce Analytics Pipeline (Simulated Streaming)

Python, Apache Kafka, Spark Streaming, Streamlit

Designed a synthetic data generator for real-time e-commerce transactions, processed the stream with Spark Streaming, and displayed live metrics in Streamlit.
Customer Churn Prediction & Decision-Support Dashboard

XGBoost, Random Forest, MLflow, Docker, FastAPI, Power BI

Built and compared XGBoost and Random Forest models on a 100K-record customer dataset, tracked experiments with MLflow, containerized the model with Docker and FastAPI, and visualized churn insights in Power BI.

Courses & certifications

Software Engineering Job Simulation · Forage
Prompt Engineering for Developers · DeepLearning.AI
Data Science: Mastering the Fundamentals · Scaler Topics

Explore the Broxer community

💬 Q&A Ask about roles, salaries and interviews — and help others. 👥 Circles Join discussions on skills, companies and industries. 📰 Feed Follow updates and insights from the community.