Vamsi Andavarapu

AI / ML Engineer · NLP & LLMs · RAG Pipelines · Data Analytics Data Science

Talent

VizianagaramMember since July 12, 2026

Scikit-learnLLMsRAGVector EmbeddingsChromaDBPythonPandasNumPyMatplotlibSeaborn

Hire this person

Send a job offer directly to this candidate

Scikit-learnLLMsRAGVector EmbeddingsChromaDB

About

Final-year B.Tech Computer Science (Data Science) undergraduate with an 8.93 CGPA and hands-on experience in building AI/ML systems, NLP pipelines, and machine learning model development. Built a RAG-powered LLM travel assistant leveraging Llama 3.2 (local), ChromaDB vector store, and semantic embeddings on a custom-curated dataset — enabling fast, context-aware itinerary recommendations without external API dependency. Seeking an AI/ML Engineer role to architect, train, evaluate, and deploy intelligent systems that drive measurable business value.

Experience

AI/ML INTERN at DEMY SOFTWARE SOLUTIONS (2024-06 – 2024-07)

Developed and evaluated 3+ regression and classification ML models using Python and scikit-learn — covering end-to-end workflow including data preprocessing, feature engineering, and model performance testing.
Applied data cleaning techniques across 3+ real-world datasets — handled missing values, encoded categorical variables, and normalized features, reducing data inconsistencies and improving model input quality.
Built a Life Expectancy Prediction system on WHO Global Health data (193 countries, 20-year span) using Linear Regression — performed EDA across 20+ features to identify key health indicators such as schooling, GDP, and immunization coverage influencing life expectancy.

DATA ANALYSIS INTERN at APSSDC — GOVT. OF ANDHRA PRADESH (2025-04 – 2025-06)

Investigated NYC Airbnb listings dataset (37,000+ entries) to uncover pricing trends, host activity, and neighborhood dynamics across five boroughs using Python, Pandas, and NumPy.
Performed end-to-end data preprocessing on a 37,000+ row dataset — handled missing values, removed outliers using IQR method, and engineered 5+ features such as price segments (Budget to Luxury) and availability status.
Derived key business insights: identified Manhattan as the highest-priced borough, examined room type demand patterns, and investigated correlation between listing price and review scores across neighborhoods.