Open to opportunities

Ravi kumar Gubbala

@ravikumargubbala

Message

Data scientist and ML engineer focused on scalable AI solutions.

India

Message

What I'm looking for

I seek roles where I can build and deploy production ML/AI systems, work across data engineering and MLOps, solve operational challenges, and grow in a collaborative, impact-driven team.

I am a data scientist and machine learning engineer who builds scalable AI solutions and production-ready models. I combine practical engineering with applied ML to deliver measurable improvements in operations and product quality.

I engineered an LLM Sandbox — a no-code platform integrating PostgreSQL, MongoDB, SharePoint, OneDrive, PDFs, vector search (Qdrant), Redis-based chat history, and numerous open-source and proprietary models to enable rapid chatbot deployment.

I have delivered domain projects including a Sugammadex yield optimizer that reduced cycle time and increased yield, NER extraction systems using AWS Textract and SpaCy, and time-series forecasting and anomaly-detection models (XGBoost, LSTM, Holt-Winters, Prophet, Chronos) deployed with Kubeflow, KServe and MLflow.

I focus on end-to-end workflows: data engineering, model development, deployment, monitoring and cost/performance benchmarking, and I have been recognized with awards for resolving critical production issues.

Experience

Work history, roles, and key accomplishments

AI Platform Engineer

LLM Sandbox

Engineered a no-code platform for rapid deployment of AI chatbots, integrated multiple data sources, implemented advanced retrieval and reranking techniques, and managed chat history and vector search for scalable conversational AI.

PostgreSQL MongoDB Redis Qdrant Vector Search Prompt Engineering

Machine Learning Engineer

Telenet

Participated in E2E acceptance and quality testing for wireline and wireless services, created test plans and automation scripts, executed test cases, logged defects in Jira, and prepared test closure reports to improve delivery quality.

Test Planning QA Automation Jira Acceptance Testing Test Execution

Data Scientist

Data Science Innovation

Analyzed time series data and developed forecasting and anomaly detection models (XGBoost, Prophet, LSTM, Chronos), deployed models with KServe and Kubeflow, and monitored model drift with MLflow.

Time Series Anomaly Detection XGBoost KServe Kubeflow MLFlow Model Monitoring

Data Scientist

Industrial Lab Projects

Built NER pipelines to extract custom entities from PDFs using AWS Textract, SpaCy and regex, and developed predictive models for student dropout and loan default integrated into production workflows.

Sagemaker SpaCy Regex NER Python

Intern / Researcher

Sugammadex Yield Optimizer

Built an application using convex optimization to maximize product yields, reducing cycle time from 10 to 8 days and increasing yield by approximately 5–10%, and provided single optimal recommendations across 100 batches.

Python Yield Optimization Data Analysis Batch Processing Process Improvement

Data Engineer

Independent Projects

Focused on web scraping, data preprocessing, feature engineering and visualization; maintained high-quality search data collection across 90 projects using Pytrends and processed Elasticsearch data for tagging.

Python Web Scraping Pytrends Elasticsearch Data Cleaning Tokenization Data Visualization

Education

Degrees, certifications, and relevant coursework

Amrita Vishwa Vidyapeetham

Bachelor of Technology, Computer Science

2017 - 2021

Grade: CGPA: 6.0

Completed a B.Tech in Computer Science with coursework in Data Science, Machine Learning, probability and statistics, and marketing research; achieved a CGPA of 6.0.