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

I am a Machine Learning Engineer with 6+ years of experience turning business requirements into scalable analytical models and production-ready ML solutions. I specialize in end-to-end ML pipelines, GenAI, and large language models, with a track record of delivering impactful analytics in fintech, utilities, banking, and insurance. I thrive in cross-functional teams, designing modular training, validation, and inference components, and prioritizing governance, latency, and reliability in enterprise environments. I’ve worked with in-database ML, RAG architectures, and deployment platforms like Azure ML, AWS SageMaker, and Databricks. My strengths include NLP, time-series analysis, clustering, and explainability, along with building robust data pipelines and CI/CD workflows that scale to millions of records.…I am a Machine Learning Engineer with 6+ years of experience turning business requirements into scalable analytical models and production-ready ML solutions. I specialize in end-to-end ML pipelines, GenAI, and large language models, with a track record of delivering impactful analytics in fintech, utilities, banking, and insurance. I thrive in cross-functional teams, designing modular training, validation, and inference components, and prioritizing governance, latency, and reliability in enterprise environments. I’ve worked with in-database ML, RAG architectures, and deployment platforms like Azure ML, AWS SageMaker, and Databricks. My strengths include NLP, time-series analysis, clustering, and explainability, along with building robust data pipelines and CI/CD workflows that scale to millions of records.

PHANI SAI K

Data Scientist, AI Engineer, Data Analyst, +5





I am a Machine Learning Engineer with 6+ years of experience turning business requirements into scalable analytical models and production-ready ML solutions. I specialize in end-to-end ML pipelines, GenAI, and large language models, with a track record of delivering impactful analytics in fintech, utilities, banking, and insurance. I thrive in cross-functional teams, designing modular training, validation, and inference components, and prioritizing governance, latency, and reliability in enterprise environments. I’ve worked with in-database ML, RAG architectures, and deployment platforms like Azure ML, AWS SageMaker, and Databricks. My strengths include NLP, time-series analysis, clustering, and explainability, along with building robust data pipelines and CI/CD workflows that scale to millions of records.…I am a Machine Learning Engineer with 6+ years of experience turning business requirements into scalable analytical models and production-ready ML solutions. I specialize in end-to-end ML pipelines, GenAI, and large language models, with a track record of delivering impactful analytics in fintech, utilities, banking, and insurance. I thrive in cross-functional teams, designing modular training, validation, and inference components, and prioritizing governance, latency, and reliability in enterprise environments. I’ve worked with in-database ML, RAG architectures, and deployment platforms like Azure ML, AWS SageMaker, and Databricks. My strengths include NLP, time-series analysis, clustering, and explainability, along with building robust data pipelines and CI/CD workflows that scale to millions of records.

Available to hire

I am a Machine Learning Engineer with 6+ years of experience turning business requirements into scalable analytical models and production-ready ML solutions. I specialize in end-to-end ML pipelines, GenAI, and large language models, with a track record of delivering impactful analytics in fintech, utilities, banking, and insurance. I thrive in cross-functional teams, designing modular training, validation, and inference components, and prioritizing governance, latency, and reliability in enterprise environments.

I’ve worked with in-database ML, RAG architectures, and deployment platforms like Azure ML, AWS SageMaker, and Databricks. My strengths include NLP, time-series analysis, clustering, and explainability, along with building robust data pipelines and CI/CD workflows that scale to millions of records.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

Machine Learning Engineer at American Express

August 1, 2024 - Present

Led development of an internal chatbot that summarizes SEC financial filings and answers user questions. Built a Retrieval-Augmented Generation (RAG) pipeline with embeddings and a vector store, designed prompts, evaluated models (BGEM3, GPT-4, Llama3) for accuracy, deployed production-grade Python code, and established Azure Databricks workflows. Created dataframes with Pandas and PySpark for structured representation and performance.

Machine Learning Engineer at BC Hydro

June 1, 2023 - August 1, 2024

Developed binary and multi-class classification models to predict safety events and hazard codes. Built sentence embeddings with BERT to cluster events, used KMeans, DBSCAN, and hierarchical clustering, implemented XGBoost classifier, leveraged AutoML in Azure ML Studio, and deployed models on Azure Kubernetes Service. Performed OCR data processing and time-series analysis of clusters; conducted anomaly detection and NLP preprocessing for logs.

Data Scientist at Verisk

May 1, 2022 - June 1, 2023

Contributed to the CRISP-DM lifecycle, built ML models for credit card fraud detection (SVM, Logistic Regression, Random Forest, Naive Bayes, MLP), performed segmentation, revenue forecasting, churn prediction, and pricing analyses, and created dashboards with Tableau. Worked with Spark (PySpark) clusters, conducted data migration from MSSQL to Salesforce, and built ETL pipelines with Azure Data Factory; collaborated with cross-functional teams and delivered production-ready models.

ML/Data Scientist at Yashitha Soft

July 1, 2018 - September 1, 2021

Led data science projects from EDA to production: built fraud detection, churn, revenue forecasting, and pricing models; used SVM, Decision Trees, Logistic Regression, Random Forest, Naive Bayes, and MLP; performed text mining and sentiment analysis; built customer segmentation via clustering; deployed models on Azure Kubernetes Service and created dashboards in Tableau; mentored peers and supported data migrations.

Data Scientist at Yashitha Soft

July 1, 2018 - September 1, 2021

Worked with banking, insurance, and utility clients to preprocess data, perform EDA, and build predictive models (fraud detection, churn, revenue forecasting). Implemented clustering, association rule mining, text mining, and sentiment analysis. Led data migration planning, data quality improvements, and visualization development in Tableau; used PySpark for large-scale data processing and implemented ML pipelines across Hadoop/Spark environments. Delivered production-ready models and dashboards to stakeholders.