Kavya sree Gurram
MSc Artificial Intelligence student with hands-on experience in machine learning and data engineering
Hire this person
Send a job offer directly to this candidate
About
MSc Artificial Intelligence student with hands-on experience preparing and integrating real-world datasets, building and validating machine learning models in Python and SQL, and presenting results to non-technical stakeholders. Improved house-price prediction accuracy from 72% to 84% by comparing regression and decision-tree models on 5,000+ records, and currently prepare CRM and property data for AI experimentation. Keen to apply machine learning and data engineering skills to sustainability and housing decarbonisation.
Experience
AI Intern at Let Sell Property (2026-05 – Present)
Translate operational challenges into defined AI use cases, gathering requirements from non-technical stakeholders and assessing where automation, predictive analytics or generative AI adds practical value.
- Prototype AI-assisted workflows for repetitive enquiries and information retrieval, using prompt engineering and structured testing to improve relevance and consistency.
- Evaluate prototype outputs against representative scenarios, documenting incorrect or inconsistent responses and iteratively refining prompts, workflow logic and input structures to improve reliability.
- Prepare CRM and property datasets for experimentation by profiling quality, standardising fields, resolving duplicates and documenting gaps.
- Investigate patterns across customer, property and operational data, converting findings into candidate features, business rules and automation opportunities.
- Document assumptions, limitations and results to create reproducible records, and explain findings to non-technical colleagues in practical business language.
- Consider data privacy, human oversight, accuracy and escalation requirements when evaluating AI applications.
Machine Learning Intern (Virtual) at Bhart Intern (2024-05 – 2024-07)
Improved house-price prediction accuracy from 72% to 84% by training and comparing regression and decision-tree models on 5,000+ property records.
- Prepared structured datasets by treating missing values and outliers, applying scaling and train-test partitioning.
- Built a movie recommendation engine using collaborative and content-based filtering.
- Compared models using RMSE, MAE and accuracy, and tuned hyperparameters and feature combinations to improve stability and prediction quality.
Education
MSc in Artificial Intelligence – University of East London (2025-09 – 2027-09)
B.Tech in Computer Science (AI & ML) – Sri Chaitanya Institute of Technology and Research (2021-10 – 2025-06)
