Sai Tejasri Yerramsetti
Summary
Data Scientist with a proven track record at SDSU Research Foundation, excelling in genomic ETL pipeline development and interactive dashboard creation. Expert in Python and Tableau, I enhance data-driven decision-making while fostering collaboration across teams. Achieved a 40% reduction in processing time, showcasing my commitment to impactful results.
Overview
4
4
years of professional experience
1
1
Certification
Work History
RESEARCH DATA SCIENTIST
SDSU Research Foundation
07.2024 - Current
- Built genomic ETL pipelines using PLINK2 and Google Cloud Platform (BigQuery, Storage), reducing processing time by 40% and accelerating cohort-wide analyses.
- Developed interactive Tableau dashboards for SNP-association visualization; boosted clinical interpretability by 30% across interdisciplinary teams.
- Partnered with statisticians and ML engineers to streamline phenotype-genotype matching workflows, enabling hypothesis testing at scale.
DATA SCIENTIST INTERN
ZIP Launchpad
01.2024 - 07.2024
- Designed time series forecasting models (ARIMA, Prophet) in Python to predict event turnout; informed resource allocation with 87% accuracy.
- Delivered Tableau/Power BI dashboards with role-based filters; improved strategic reporting velocity by 30% across product and marketing and conducted A/B testing survey analytics, increasing classification accuracy by 20%.
DATA SCIENTIST INTERN
Digital Innovation Lab
06.2023 - 08.2023
- Created a GenAI-enabled chatbot using TogetherAI API and LangChain; scaled to 10K+ sessions with 40% user retention increase.
- Integrated vector search and semantic search using ChromaDB and LangChain to improve retrieval precision in RAG workflows.
- Fine-tuned Mistral 7B using PyTorch and RLHF techniques for sentiment inference; decreased latency by 20% in high-traffic pipelines.
- Built a PySpark-based feedback analytics platform on AWS EC2 GPU; enabled real-time insight ingestion and reduced response lag by 25%.
AI SOFTWARE ENGINEER
Temenos
08.2021 - 08.2023
- Built anomaly detection systems using XGBoost and LightGBM to monitor transaction fraud; improved accuracy by 22% and reduced manual review by 35%.
- Created time series forecasting pipelines (LSTM, ARIMA, Prophet) in PySpark and SQL; reached 90% forecasting accuracy across 5 regions.
- Automated MLOps life cycle using MLflow, Docker, and Jenkins; slashed model deployment time by 38%.
- Streamed 100M+ sensor events daily via Spark + Kafka + Azure Synapse; decreased ETL latency by 6 hours.
Education
Master of Science - Big Data Analytics
San Diego State University
San Diego, USA05.2025
Bachelor of Technology - Electronics and Communication Engineering
Sagi Ramakrishnam Raju Engineering College
India07.2021
Skills
Programming Languages: Python, SQL, R, Java, C, Rust
Databases and Frameworks: MySQL, PostgreSQL, MongoDB, Flask, Snowflake, NoSQL, ChromaDB, Pinecone, SQLite, Kubernetes, FastAPI, Langgraph, LlamaIndex, CrewAI, SAS, Kafka, AirFlow, MLflow ML/DL: KNN, RNN, CNN, Transformers, BERT, GPT-4,LLaMa
Libraries: TensorFlow, PyTorch, Keras, Matplotlib, Seaborn, PySpark, Spacy, Numpy, Pandas, SciPy, OpenAI, NLTK, MLlib, OpenCV, BeautifulSoup, Scikit-Learn, Streamlit, Git, Bitbucket, Transformers, NLP
Technologies and Tools: Selenium, AWS (EC2, S3, RDS, Lambda, SageMaker), Azure (Data Factory, Data Lake, Databricks, Blob Storage), GCP (GCS, Dataflow, BigQuery, Vertex AI), GitHub, Apache Spark, Excel, Agile,
Tableau, Sigma, Looker, Power Bi, Microsoft Fabric
Certification
- Oracle Cloud Infrastructure 2024 GenAI Professional
- Databricks Academy Accreditation - GenAI Fundamentals
- Google Data Analytics Professional Certificate (2025)
Projects And Publications
- IEEE Paper - Human Emotion Classification using RNNs and KNN, IEEE Xplore, 04/01/22
- Credit Card Fraud Detection, Journal of Emerging Technologies, 2021
- Multi PDFs Chatbot AI Agent, Developed a Streamlit-based AI chatbot app integrating LangChain, FAISS, and Google Gemini Pro for real-time semantic QA across multiple PDFs using RAG and adaptive chunking.
- AI-Powered Portfolio Generator, Developed an end-to-end application using Streamlit, Anthropic Claude API, and PDF/HTML processing to extract resume content and dynamically generate a professional portfolio website for users., [link]
- Feedback Processing API, Built a Flask-based API for audio feedback processing, including transcription, summarization, sentiment analysis, categorization, and keyword extraction. Integrated Google Cloud Speech-to-Text and multiple NLP models for end-to-end text analysis., [link]
Timeline
RESEARCH DATA SCIENTIST
SDSU Research Foundation
07.2024 - Current
DATA SCIENTIST INTERN
ZIP Launchpad
01.2024 - 07.2024
DATA SCIENTIST INTERN
Digital Innovation Lab
06.2023 - 08.2023
AI SOFTWARE ENGINEER
Temenos
08.2021 - 08.2023
Master of Science - Big Data Analytics
San Diego State University
Bachelor of Technology - Electronics and Communication Engineering
Sagi Ramakrishnam Raju Engineering College
Similar Profiles
Allisyn MarksAllisyn Marks
Laboratory Assistant II at SDSU Research FoundationLaboratory Assistant II at SDSU Research Foundation
Magdalena MorganMagdalena Morgan
Administrative Support Assistant at SDSU Research FoundationAdministrative Support Assistant at SDSU Research Foundation
Kimberly MirandaKimberly Miranda
Grant Specialist (GS) IV at SDSU Research Foundation (SDSURF)Grant Specialist (GS) IV at SDSU Research Foundation (SDSURF)
ROMAN POPOVROMAN POPOV
RESEARCH DATA SCIENTIST at Cleveland ClinicRESEARCH DATA SCIENTIST at Cleveland Clinic
JAIKISHAN KHATRIJAIKISHAN KHATRI
Research Data Scientist at LabLENIResearch Data Scientist at LabLENI