Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am a passionate and skilled Machine Learning Engineer currently pursuing my Master of Science in Artificial Intelligence at Rochester Institute of Technology. With solid experience in building AI pipelines on AWS and deploying machine learning models at scale, I thrive on solving complex challenges in document AI, semantic search, and real-time analytics. My background includes deep expertise in natural language processing and cloud architectures, which helps me design robust and cost-effective AI-driven solutions. In addition to my professional work, I am actively involved in research on explainable AI techniques and healthcare predictive modeling. I enjoy collaborating across teams to align AI technologies with business requirements and stakeholder goals. With a strong foundation in software engineering and MLOps, I continuously seek to optimize and innovate through best practices in AI deployment and monitoring.…I am a passionate and skilled Machine Learning Engineer currently pursuing my Master of Science in Artificial Intelligence at Rochester Institute of Technology. With solid experience in building AI pipelines on AWS and deploying machine learning models at scale, I thrive on solving complex challenges in document AI, semantic search, and real-time analytics. My background includes deep expertise in natural language processing and cloud architectures, which helps me design robust and cost-effective AI-driven solutions. In addition to my professional work, I am actively involved in research on explainable AI techniques and healthcare predictive modeling. I enjoy collaborating across teams to align AI technologies with business requirements and stakeholder goals. With a strong foundation in software engineering and MLOps, I continuously seek to optimize and innovate through best practices in AI deployment and monitoring.

Tulasi Venkata Sri Varshini Padamata

AI Engineer, Data Scientist, Developer, +1





I am a passionate and skilled Machine Learning Engineer currently pursuing my Master of Science in Artificial Intelligence at Rochester Institute of Technology. With solid experience in building AI pipelines on AWS and deploying machine learning models at scale, I thrive on solving complex challenges in document AI, semantic search, and real-time analytics. My background includes deep expertise in natural language processing and cloud architectures, which helps me design robust and cost-effective AI-driven solutions. In addition to my professional work, I am actively involved in research on explainable AI techniques and healthcare predictive modeling. I enjoy collaborating across teams to align AI technologies with business requirements and stakeholder goals. With a strong foundation in software engineering and MLOps, I continuously seek to optimize and innovate through best practices in AI deployment and monitoring.…I am a passionate and skilled Machine Learning Engineer currently pursuing my Master of Science in Artificial Intelligence at Rochester Institute of Technology. With solid experience in building AI pipelines on AWS and deploying machine learning models at scale, I thrive on solving complex challenges in document AI, semantic search, and real-time analytics. My background includes deep expertise in natural language processing and cloud architectures, which helps me design robust and cost-effective AI-driven solutions. In addition to my professional work, I am actively involved in research on explainable AI techniques and healthcare predictive modeling. I enjoy collaborating across teams to align AI technologies with business requirements and stakeholder goals. With a strong foundation in software engineering and MLOps, I continuously seek to optimize and innovate through best practices in AI deployment and monitoring.

Available to hire

I am a passionate and skilled Machine Learning Engineer currently pursuing my Master of Science in Artificial Intelligence at Rochester Institute of Technology. With solid experience in building AI pipelines on AWS and deploying machine learning models at scale, I thrive on solving complex challenges in document AI, semantic search, and real-time analytics. My background includes deep expertise in natural language processing and cloud architectures, which helps me design robust and cost-effective AI-driven solutions.

In addition to my professional work, I am actively involved in research on explainable AI techniques and healthcare predictive modeling. I enjoy collaborating across teams to align AI technologies with business requirements and stakeholder goals. With a strong foundation in software engineering and MLOps, I continuously seek to optimize and innovate through best practices in AI deployment and monitoring.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Work Experience

Machine Learning Engineer at Novacis Digital

May 1, 2024 - August 27, 2025

Built a document AI pipeline on AWS SageMaker using LayoutLM and BERT, significantly improving accuracy on over 10,000 legal documents and automating entity extraction. Deployed a multimodal OCR plus large language model (LLM) service with FastAPI on Amazon EKS integrated with S3 and CloudWatch, reducing manual review time from hours to minutes. Developed semantic search with Sentence Transformers, FAISS, and DynamoDB enabling near real-time lookups and greater query efficiency. Integrated GPT-4 and Claude APIs for contract summarization and compliance checks while evaluating deployment strategies to reduce cost and boost reliability. Collaborated closely with data engineering and legal teams to align AWS pipelines with business workflows, ensuring stakeholder adoption and operational stability.

Undergraduate Research Assistant at RMK Research Lab

May 1, 2023 - August 27, 2025

Explored explainable AI methods for cardiovascular disease prediction using ensemble models coupled with LIME interpretability techniques. Implemented ECG signal feature extraction and constructed machine learning ensembles that enhanced detection accuracy of right ventricular dysfunction beyond individual models. Developed end-to-end ML pipelines with XGBoost, Random Forest, and Gradient Boosting achieving robust predictive performance on clinical datasets. Evaluated models using accuracy (93.1%) and ROC-AUC (0.95) on over 1,190 patient records demonstrating improvements relative to AdaBoost and CatBoost baselines.