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

Hi, I'm Sriram Sannapareddy, an AI/ML engineer based in Santa Clara, California. I design and productionize scalable ML and LLM-powered systems for fraud detection, risk analytics, and recommendation platforms. I specialize in building real-time data pipelines, feature engineering, and end-to-end MLOps using Databricks, Spark, Azure, and AWS to translate business problems into AI-driven solutions that boost efficiency and improve customer experience. In my work, I focus on reliability, governance, and explainability—developing conversational AI, risk decisioning models, and analytics dashboards that empower risk, compliance, and business leadership with actionable insights. I enjoy collaborating across data governance, cybersecurity, and product teams to deliver impact at scale.…Hi, I'm Sriram Sannapareddy, an AI/ML engineer based in Santa Clara, California. I design and productionize scalable ML and LLM-powered systems for fraud detection, risk analytics, and recommendation platforms. I specialize in building real-time data pipelines, feature engineering, and end-to-end MLOps using Databricks, Spark, Azure, and AWS to translate business problems into AI-driven solutions that boost efficiency and improve customer experience. In my work, I focus on reliability, governance, and explainability—developing conversational AI, risk decisioning models, and analytics dashboards that empower risk, compliance, and business leadership with actionable insights. I enjoy collaborating across data governance, cybersecurity, and product teams to deliver impact at scale.

Sriram Sannapareddy

AI Engineer, Data Scientist, Data Analyst, +2





Hi, I'm Sriram Sannapareddy, an AI/ML engineer based in Santa Clara, California. I design and productionize scalable ML and LLM-powered systems for fraud detection, risk analytics, and recommendation platforms. I specialize in building real-time data pipelines, feature engineering, and end-to-end MLOps using Databricks, Spark, Azure, and AWS to translate business problems into AI-driven solutions that boost efficiency and improve customer experience. In my work, I focus on reliability, governance, and explainability—developing conversational AI, risk decisioning models, and analytics dashboards that empower risk, compliance, and business leadership with actionable insights. I enjoy collaborating across data governance, cybersecurity, and product teams to deliver impact at scale.…Hi, I'm Sriram Sannapareddy, an AI/ML engineer based in Santa Clara, California. I design and productionize scalable ML and LLM-powered systems for fraud detection, risk analytics, and recommendation platforms. I specialize in building real-time data pipelines, feature engineering, and end-to-end MLOps using Databricks, Spark, Azure, and AWS to translate business problems into AI-driven solutions that boost efficiency and improve customer experience. In my work, I focus on reliability, governance, and explainability—developing conversational AI, risk decisioning models, and analytics dashboards that empower risk, compliance, and business leadership with actionable insights. I enjoy collaborating across data governance, cybersecurity, and product teams to deliver impact at scale.

Available to hire

Hi, I’m Sriram Sannapareddy, an AI/ML engineer based in Santa Clara, California. I design and productionize scalable ML and LLM-powered systems for fraud detection, risk analytics, and recommendation platforms. I specialize in building real-time data pipelines, feature engineering, and end-to-end MLOps using Databricks, Spark, Azure, and AWS to translate business problems into AI-driven solutions that boost efficiency and improve customer experience.

In my work, I focus on reliability, governance, and explainability—developing conversational AI, risk decisioning models, and analytics dashboards that empower risk, compliance, and business leadership with actionable insights. I enjoy collaborating across data governance, cybersecurity, and product teams to deliver impact at scale.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Work Experience

AI/ML Engineer at Databricks

November 1, 2024 - Present

Architected and productionized real-time credit card fraud detection pipelines on Azure Databricks using Kafka, Spark Structured Streaming, Delta Lake, and MLflow, reducing false positives by 35% across enterprise payment systems. Engineered LLM-based risk classification pipelines using Hugging Face Transformers and Azure Machine Learning, scaling automated risk decisioning to 5M+ users and reducing processing time by 60%. Designed an LLM-powered conversational AI system for transaction verification using prompt engineering, LangChain, and OpenAI APIs, improving intent recognition accuracy by 45% and increasing customer satisfaction scores by 30%. Architected end-to-end MLOps pipelines for model retraining, deployment, and rollback using MLflow, Terraform, and Databricks Jobs, reducing release time by 50% and improving traceability, reproducibility, and compliance.

AI/ML Engineer at Trigma

September 1, 2020 - July 1, 2023

Built and deployed production-ready hybrid recommendation engine using LightFM for collaborative filtering and FAISS for vector similarity search, leveraging Redis caching for low-latency retrieval, increasing user engagement by 17% and session duration by 20%. Developed and evaluated churn prediction models to identify at-risk learners, reducing student churn by 18%. Designed and deployed automated end-to-end ML pipelines on AWS (EC2, S3, Lambda), implementing CI/CD, scheduled model retraining, and real-time monitoring to enable scalable, low-latency model inference in production. Integrated ML-driven analytics into React dashboards and instructor tools for real-time insights; implemented automated model monitoring and explainability using SHAP to track performance, detect data drift and trigger alerts. Engineered reproducible ML workflows using Git and DVC for data and model versioning, enabling scalable experimentation.