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

Senior Data Scientist with around 5 years of experience building large-scale machine learning and Generative AI systems across conversational AI, financial fraud detection, and healthcare analytics platforms. Specialized in LLM infrastructure, retrieval-augmented generation (RAG), and distributed ML pipelines supporting millions of users. Delivered production AI systems automating 2.8M+ monthly customer interactions and built fraud detection platforms preventing $40K+ in annual financial losses while improving operational decision intelligence. Experienced in deploying cloud-native ML platforms, real-time inference services, and scalable data pipelines across enterprise environments.…Senior Data Scientist with around 5 years of experience building large-scale machine learning and Generative AI systems across conversational AI, financial fraud detection, and healthcare analytics platforms. Specialized in LLM infrastructure, retrieval-augmented generation (RAG), and distributed ML pipelines supporting millions of users. Delivered production AI systems automating 2.8M+ monthly customer interactions and built fraud detection platforms preventing $40K+ in annual financial losses while improving operational decision intelligence. Experienced in deploying cloud-native ML platforms, real-time inference services, and scalable data pipelines across enterprise environments.

Dishen Patel

Data Scientist, AI Engineer, Data Engineer, +1





Senior Data Scientist with around 5 years of experience building large-scale machine learning and Generative AI systems across conversational AI, financial fraud detection, and healthcare analytics platforms. Specialized in LLM infrastructure, retrieval-augmented generation (RAG), and distributed ML pipelines supporting millions of users. Delivered production AI systems automating 2.8M+ monthly customer interactions and built fraud detection platforms preventing $40K+ in annual financial losses while improving operational decision intelligence. Experienced in deploying cloud-native ML platforms, real-time inference services, and scalable data pipelines across enterprise environments.…Senior Data Scientist with around 5 years of experience building large-scale machine learning and Generative AI systems across conversational AI, financial fraud detection, and healthcare analytics platforms. Specialized in LLM infrastructure, retrieval-augmented generation (RAG), and distributed ML pipelines supporting millions of users. Delivered production AI systems automating 2.8M+ monthly customer interactions and built fraud detection platforms preventing $40K+ in annual financial losses while improving operational decision intelligence. Experienced in deploying cloud-native ML platforms, real-time inference services, and scalable data pipelines across enterprise environments.

Available to hire

Senior Data Scientist with around 5 years of experience building large-scale machine learning and Generative AI systems across conversational AI, financial fraud detection, and healthcare analytics platforms. Specialized in LLM infrastructure, retrieval-augmented generation (RAG), and distributed ML pipelines supporting millions of users.

Delivered production AI systems automating 2.8M+ monthly customer interactions and built fraud detection platforms preventing $40K+ in annual financial losses while improving operational decision intelligence. Experienced in deploying cloud-native ML platforms, real-time inference services, and scalable data pipelines across enterprise environments.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Work Experience

Sr. Data Scientist at Amazon

October 1, 2025 - Present

Led development of LLM-powered conversational support agents for Alexa services, designing scalable response automation workflows that process 2.8M+ monthly voice and chat interactions and reduce manual support workload by 1.2M tickets annually. Designed and implemented a production Retrieval-Augmented Generation architecture integrating enterprise knowledge bases with hybrid semantic retrieval (FAISS + OpenSearch), improving contextual answer accuracy by 28% across Alexa support workflows. Built distributed NLP preprocessing and embedding pipelines using PyTorch and Spark to generate semantic representations across large conversational datasets. Architected low-latency vector retrieval infrastructure across millions of historical interactions, optimizing hybrid search ranking and reducing semantic search latency by 40% for real-time conversational queries. Deployed cloud-native LLM inference services with containerized APIs and scalable orchestration on Azure infrastructure, supportin

Data Scientist at Accenture

February 1, 2022 - August 31, 2024

Developed a real-time fraud detection platform using Python, SQL, and scikit-learn analyzing 8M+ financial transactions, improving fraud risk detection and reducing fraudulent approvals by 32% through predictive transaction scoring. Engineered large-scale behavioral feature engineering pipelines using PySpark and distributed SQL capturing device fingerprints, transaction velocity signals, and merchant risk features. Implemented LSTM-based sequential fraud detection models in TensorFlow to identify account takeover and card testing patterns across 1.5M+ customer accounts. Designed and deployed a real-time fraud scoring API using Python, Docker, and AWS SageMaker for low-latency inference to automate transaction risk decisions and prevent estimated $40K+ in annual fraudulent losses. Applied unsupervised anomaly detection techniques including Isolation Forest and Autoencoders to identify emerging fraud patterns and previously unseen attack vectors.

Jr. Data Scientist at Accenture

January 1, 2021 - January 31, 2022

Developed an end-to-end healthcare risk prediction platform using Python, Pandas, NumPy, and SQL analyzing 10M+ insurance claims and patient records, improving preventive care targeting accuracy by 31%. Engineered distributed feature engineering pipelines using PySpark and Delta Lake on AWS to process multi-terabyte healthcare datasets. Built predictive ML models including XGBoost, Random Forest, and Logistic Regression to predict chronic disease risk and hospital readmission probability, improving intervention targeting accuracy by 26%. Developed deep learning models using RNN architectures for longitudinal patient health records across 2M+ members, improving care gap detection and treatment adherence predictions by 21%. Designed statistical evaluation frameworks to validate population health interventions and reduce prediction bias across demographic groups by 17%. Implemented real-time healthcare data pipelines using Kafka, AWS S3, and Spark Structured Streaming enabling near real-t