Data Science Scientist

Vamsi Krishna Yerubandi

713-***-**** ********@*****.*** linkedin.com/in/y-vamsi-krishna github.com/vamsiy2001 OBJECTIVE

Graduate student in Data Science with 2+ years of industry experience in applied AI and software development. Passionate about Generative AI, LLM customization, and intelligent agents. Actively exploring AI agent frameworks (LangGraph), custom-tuned LLMs, and real-world applications of GenAI to deliver scalable, impactful solutions. Seeking 2025 full-time opportunities in AI/ML and Data Science. Experience

Associate Data Scientist July 2022 – Dec 2023

Innominds Software Pvt Ltd Hyderabad, India

– Designed and deployed large-scale PDF data extraction pipelines (95%+ accuracy) using OCR and Dockerized services, improving document processing speed by 40%.

– Developed deep learning models for multi-class object detection with 90%+ accuracy, enabling automation in defect detection and image classification use cases.

– Contributed to Generative AI initiatives by fine-tuning and evaluating models for text extraction and document understanding across noisy datasets.

App Development Intern June 2021 – Sept 2021

Nibrus Technologies Pvt Ltd Remote

– Built an Android app with Flutter/Dart and Firebase backend, enabling seamless user authentication and real-time data synchronization.

– Enhanced user engagement by designing intuitive UI/UX components, improving app adoption among target users.

– Collaborated with cross-functional teams, managing GitLab-based version control and ensuring timely feature delivery.

Data Science Intern May 2021 – July 2021

Gibbr Technologies Pvt Ltd Remote

– Performed exploratory data analysis and visualization, generating actionable insights for client reports.

– Engineered data pipelines for preprocessing and statistical modeling, streamlining decision-support workflows.

– Built predictive ML models to forecast user behaviors, supporting client-facing recommendations. Projects

AI Chatbot Agents with LangGraph and Human-in-the-Loop Assistance 2025

– Built chatbot pipelines leveraging LangGraph, integrating LLM reasoning with human feedback for error recovery.

– Implemented context management, conversation memory, and retrieval-augmented generation (RAG) for improved response accuracy.

Bilingual Machine Translation (English-Spanish) using Bi-LSTM Nov 2024 – Dec 2024

– Trained a Bi-LSTM translation model on Tatoeba (140k sentence pairs). Incorporated attention and layer normalization to improve context retention, achieving a 0.55 ROUGE-1 score.

– Applied L2 regularization with optimization strategies, which strengthened generalization and reduced overfitting Automated Airway Bill Extraction (Celebi Airlines) June 2023 – Nov 2023

– Benchmarked OCR engines (Tesseract, Google, Azure) for noisy document extraction. Demonstrated Azure OCR delivered superior recognition accuracy in degraded conditions.

– Automated structured data extraction from complex airway bills using Azure Form Recognizer, which reduced manual data entry workload and improved overall processing efficiency. Education

University Of Houston, Houston, TX Jan 2024 – Dec 2025 M.S in Engineering Data Science GPA: 3.81/4.0

Contact this candidate