Looking for a job

Sai Niharika Kukatla

@sainiharikakukatla

Data Scientist and ML Engineer at Walmart building retail forecasting models and RAG pipelines for product catalogs.

At Walmart, I develop end-to-end machine learning models for retail demand forecasting, sales prediction, customer segmentation, and churn prediction. My work has improved model precision and recall by up to 40%, and I designed RAG pipelines for enterprise product catalogs that improved contextual retrieval relevance by approximately 30%.

Previously, at Bank of America, I developed predictive and deep learning models for customer behavior, forecasting, and fraud detection. At Virtusa, I built healthcare ML pipelines and patient segmentation models; at Genpact, I worked on forecasting, NLP, and predictive analytics as a Data Scientist intern.

Experience

Work history, roles, and key accomplishments

Current

Data Scientist – ML Engineer

Current

Walmart

Jul 2025 - Present (1 year 4 months)

Designed and developed end-to-end machine learning models for retail demand forecasting, sales prediction, customer segmentation, and churn prediction. Implemented RAG pipelines and fine-tuned LLMs to improve retrieval and response quality.

Python AWS Sagemaker AWS GCP scikit learn Keras TensorFlow PyTorch XGBoost Pinecone Weaviate Faiss RAG LLM Prompt Engineering Docker Jenkins CI CD

Data Scientist

Bank of America

May 2024 - May 2025 (1 year)

Performed EDA on large-scale financial datasets and built predictive models for customer behavior and retention. Developed deep learning models and anomaly detection solutions to improve forecasting accuracy and reduce false positives.

Python SQL EDA Feature Engineering Hyperparameter Tuning Docker Kubernetes ANN RNN LSTM GRU Transformers Isolation Forest Autoencoder Random Forest XGBoost ARIMA Prophet

Data Scientist

Virtusa

Feb 2021 - Aug 2023 (2 years 6 months)

Built end-to-end scalable ML pipelines for healthcare data and developed predictive models using machine learning and deep learning. Worked with GCP services and designed REST APIs to expose model outputs.

Python SQL NoSQL PCA Machine Learning Deep Learning REST APIs GCP BigQuery Dataflow Pub Sub Cloud Functions Google Data Fusion K Means Classification

Data Scientist Intern

Genpact

Apr 2020 - Feb 2021 (10 months)

Analyzed large-scale structured datasets using SQL and Python, performed data cleaning and preprocessing, and applied machine learning models for forecasting and classification. Developed end-to-end ML pipelines and evaluated model performance.