I am Thanmaya Sri Sigireddi, a Senior Data Scientist and AIML Engineer with 9+ years of experience designing and deploying AI-powered solutions across healthcare, retail, and financial services. I specialize in deep learning, NLP, and MLOps, and I have hands-on experience deploying LLM-based solutions across cloud platforms such as AWS, Azure, and GCP. I thrive on optimizing model performance, automating ML pipelines, and building scalable AI systems that deliver measurable impact. I enjoy collaborating with domain experts to translate complex business needs into robust, transparent AI solutions. I’m passionate about model interpretability, governance, and building production-grade ML workflows that are maintainable, auditable, and secure.

Thanmaya Sri Sigireddi

I am Thanmaya Sri Sigireddi, a Senior Data Scientist and AIML Engineer with 9+ years of experience designing and deploying AI-powered solutions across healthcare, retail, and financial services. I specialize in deep learning, NLP, and MLOps, and I have hands-on experience deploying LLM-based solutions across cloud platforms such as AWS, Azure, and GCP. I thrive on optimizing model performance, automating ML pipelines, and building scalable AI systems that deliver measurable impact. I enjoy collaborating with domain experts to translate complex business needs into robust, transparent AI solutions. I’m passionate about model interpretability, governance, and building production-grade ML workflows that are maintainable, auditable, and secure.

Available to hire

I am Thanmaya Sri Sigireddi, a Senior Data Scientist and AIML Engineer with 9+ years of experience designing and deploying AI-powered solutions across healthcare, retail, and financial services. I specialize in deep learning, NLP, and MLOps, and I have hands-on experience deploying LLM-based solutions across cloud platforms such as AWS, Azure, and GCP. I thrive on optimizing model performance, automating ML pipelines, and building scalable AI systems that deliver measurable impact.

I enjoy collaborating with domain experts to translate complex business needs into robust, transparent AI solutions. I’m passionate about model interpretability, governance, and building production-grade ML workflows that are maintainable, auditable, and secure.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
Expert
See more

Language

English
Advanced

Work Experience

Senior AI/ML Data Scientist at Converse
April 1, 2024 - November 21, 2025
Led end-to-end design and deployment of scalable AI/ML solutions for healthcare analytics. Built ETL pipelines with Informatica IDMC to extract and harmonize patient and clinical data from multiple sources into Snowflake, with Streams/Tasks for near real-time updates. Developed PL/SQL procedures for automated cleansing, deduplication, and auditing, reducing ETL load times by 30%. Integrated Informatica Cloud with AWS S3 and Redshift for hybrid data transfers. Deployed inference APIs via FastAPI, Docker, and AWS ECS to serve models across distributed healthcare systems. Automated retraining and monitoring using MLflow, Kubernetes, Terraform, and CI/CD. Integrated Triton and vLLM to accelerate GPU-based LLM deployments. Built PHI-compliant ETL workflows with Airflow and AWS Glue. Enhanced NLP via SpaCy/NLTK for medical entity extraction and normalization. Used transfer learning with TensorFlow and Hugging Face Transformers; added SHAP, LIME for explainability. Implemented real-time anoma
Data Scientist at Broadridge
March 1, 2024 - March 1, 2024
Designed and maintained data integration workflows connecting AWS data lakes with Oracle and Snowflake data warehouses using Informatica IDMC. Developed PL/SQL procedures and Oracle triggers to automate data validation and transformation for credit and risk analytics. Built Snowflake ELT processes with Streams and Tasks for daily data refresh; migrated legacy SQL Server ETL to Informatica Cloud (IICS) for reliability and scalability. Reduced ETL runtime by 40% through query optimization. Applied XGBoost, LightGBM, and ensemble methods to improve predictive performance across customer scoring. Built NLP-driven document classification pipelines using SpaCy, BERT, and AWS Comprehend for key entity extraction. Enhanced explainability with SHAP and LIME; created dashboards in Power BI. Deployed Agentic AI modules to automate compliance checks and report generation. Set up fraud alerts via AWS Lambda and Step Functions. Forged forecasting pipelines with Redshift, PostgreSQL, and TensorFlow;
ML Engineer at Safeway
November 1, 2021 - November 1, 2021
Developed data ingestion and transformation pipelines with Informatica Cloud (IDMC) for financial transactions. Integrated Snowflake with PL/SQL modules for warehouse aggregation and forecasting model inputs. Converted Python data preparation scripts to Informatica mappings for maintainability. Implemented sentiment analysis and NLP workflows using BERT, SpaCy, and Hugging Face to interpret market signals. Built real-time trading signal systems using PyTorch, Apache Beam, and GCP Dataflow. Engineered scalable inference architectures with Docker, Kubernetes, and GKE; integrated vLLM and Triton for low-latency serving across GPU nodes. Automated data ingestion with Airflow and Google Cloud Storage. Applied ensemble models (XGBoost, LightGBM, Random Forest) for investment insights. Implemented Agentic AI workflows enabling autonomous trading decisions and risk assessments. Enhanced explainability with SHAP/LIME; dashboards with Power BI and Tableau over BigQuery. Established end-to-end ML
ML Analyst at Newton Software Pvt Ltd
October 1, 2019 - October 1, 2019
Developed data transformation workflows in Informatica PowerCenter and PL/SQL to integrate customer feedback and analytics data. Designed ETL mappings and workflows for structured and unstructured data ingestion into Snowflake. Tuned Oracle SQL queries for performance optimization in reporting and downstream ML pipelines. Automated data cleansing and tokenization with Python (Pandas/Numpy) for feature engineering. Built custom NER models using Stanford CoreNLP and SpaCy for domain data extraction. Created interactive dashboards with Power BI and Excel to present text insights. Deployed ML models in Docker; maintained versions via SVN. Built document clustering with KMeans and TF-IDF; integrated model outputs into Flask APIs for search/recommendation features. Enhanced model evaluation with cross-validation and GridSearchCV/RandomizedSearchCV. Developed custom text vectorization with Gensim/Word2Vec; applied LDA topic modeling. Automated Power BI and Excel reports; documented methodolog
NLP Engineer at Harman Connected Service
April 1, 2017 - April 1, 2017
Created Informatica IDMC mappings and PL/SQL procedures to load data into Snowflake and Oracle warehouses for reporting. Automated daily ETL jobs with Informatica Cloud to populate Power BI dashboards. Followed Agile SDLC; documented data flow designs and performed peer code reviews. Designed performance-tuned PL/SQL packages to optimize data refresh and analytics queries. Automated data transformation using Python (Pandas, Jupyter) to improve data quality. Validated statistical models via cross-validation and metrics using Scikit-learn and NumPy. Optimized SQL Server query performance for faster BI reporting. Implemented data versioning with Git and Power BI. Performed EDA with Matplotlib and Seaborn. Built forecasting pipelines using Prophet and Scikit-learn to predict inventory and demand. Collaborated with cross-functional teams using Git/JIRA to define data quality and validation rules. Implemented anomaly detection with Isolation Forest and TensorFlow. Delivered automated reports

Education

Bachelor of Technology (B.Tech) in Information Technology at VNRVJIET, Hyderabad, Telangana, India
January 11, 2030 - January 1, 2016

Qualifications

Add your qualifications or awards here.

Industry Experience

Healthcare, Financial Services, Software & Internet, Retail, Professional Services