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

I am Lalithya Ravuri, a Senior Python and Generative AI Engineer with 10+ years of IT experience spanning Banking, Insurance, Healthcare, and Government domains. I focus on building scalable, governance-friendly AI solutions that deliver measurable business value while meeting regulatory and operational requirements. I bring hands-on expertise across Python, GenAI, AI service design, and end-to-end ML workflows. I design secure, production-grade APIs and AI platforms, orchestrate multi-step LLM workflows, and empower enterprise teams with robust MLOps, observability, and compliance controls to enable responsible, scalable AI at scale.…I am Lalithya Ravuri, a Senior Python and Generative AI Engineer with 10+ years of IT experience spanning Banking, Insurance, Healthcare, and Government domains. I focus on building scalable, governance-friendly AI solutions that deliver measurable business value while meeting regulatory and operational requirements. I bring hands-on expertise across Python, GenAI, AI service design, and end-to-end ML workflows. I design secure, production-grade APIs and AI platforms, orchestrate multi-step LLM workflows, and empower enterprise teams with robust MLOps, observability, and compliance controls to enable responsible, scalable AI at scale.

Lalithya Ravuri

AI Engineer, Data Scientist, Full Stack Developer, +3





I am Lalithya Ravuri, a Senior Python and Generative AI Engineer with 10+ years of IT experience spanning Banking, Insurance, Healthcare, and Government domains. I focus on building scalable, governance-friendly AI solutions that deliver measurable business value while meeting regulatory and operational requirements. I bring hands-on expertise across Python, GenAI, AI service design, and end-to-end ML workflows. I design secure, production-grade APIs and AI platforms, orchestrate multi-step LLM workflows, and empower enterprise teams with robust MLOps, observability, and compliance controls to enable responsible, scalable AI at scale.…I am Lalithya Ravuri, a Senior Python and Generative AI Engineer with 10+ years of IT experience spanning Banking, Insurance, Healthcare, and Government domains. I focus on building scalable, governance-friendly AI solutions that deliver measurable business value while meeting regulatory and operational requirements. I bring hands-on expertise across Python, GenAI, AI service design, and end-to-end ML workflows. I design secure, production-grade APIs and AI platforms, orchestrate multi-step LLM workflows, and empower enterprise teams with robust MLOps, observability, and compliance controls to enable responsible, scalable AI at scale.

Available to hire

I am Lalithya Ravuri, a Senior Python and Generative AI Engineer with 10+ years of IT experience spanning Banking, Insurance, Healthcare, and Government domains. I focus on building scalable, governance-friendly AI solutions that deliver measurable business value while meeting regulatory and operational requirements.

I bring hands-on expertise across Python, GenAI, AI service design, and end-to-end ML workflows. I design secure, production-grade APIs and AI platforms, orchestrate multi-step LLM workflows, and empower enterprise teams with robust MLOps, observability, and compliance controls to enable responsible, scalable AI at scale.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Work Experience

Senior Python & Generative AI Engineer at Fiserv

January 1, 2024 - Present

Designed and deployed an enterprise Generative AI banking platform (Python 3.14) using Azure OpenAI (GPT-5) to support fraud analysis, payments, and customer service automation across high-volume financial workflows, processing over 3M interactions per month with auditable and compliant responses. Built real-time fraud intelligence pipelines, secure FastAPI services, and scalable backends on AKS with OAuth2/JWT/RBAC. Implemented Retrieval Augmented Generation (RAG) and semantic search (Pinecone/FAISS) with LangChain pipelines to reduce hallucinations, improve relevance, and accelerate dispute workflows. Delivered document intelligence with HF Transformers, LoRA-based fine-tuning, MLflow for experiment tracking, and governance controls for regulated banking environments.

Python & AI Engineer at State Farm

September 1, 2022 - December 31, 2023

Built an AI-powered chatbot platform using Python 3.10, LLMs, and AWS Bedrock to automate policy and claims servicing while aligning with ACORD/NAIC guidelines. Implemented structured conversational flows, API contracts, and fallback strategies with REST APIs and microservices, achieving 40% automated containment. Created RAG pipelines over 500k SOPs in S3 using FAISS, and developed prompts with LangChain and Hugging Face to stabilize intent understanding. Trained and deployed models on AWS SageMaker with MLOps for versioning and monitored inference (accuracy > 90%). Enhanced security with OAuth2/JWT/IAM and TLS, and established observability with CloudWatch.

Data Scientist at State of North Carolina

February 1, 2020 - July 31, 2022

Implemented KPI and Program Monitoring Framework using Python 3.7 and SQL to track 25+ compliance, risk, and outcome metrics. Built FWA analytics on medical claims using Pandas and Spark 3, reducing false positives by 20%. Developed end-to-end ETL pipelines with PySpark/SQL handling 10M+ records per run, enabling repeatable workflows aligned to HL7 and FHIR. Established centralized Data Quality Framework with Apache Griffin, improving data reliability and HIPAA/HITRUST-aligned privacy controls. Delivered Document Intelligence with Chroma embeddings improving audit readiness by 35% and governance dashboards in Looker improving decision-making by 30%.

Senior Data Engineer at Banner Health

January 1, 2017 - June 30, 2019

Operated a large-scale Big Data platform (Spark 3 and HDFS) processing claims, EDI X12, and HL7 data for enterprise analytics. Developed Scala ETL pipelines and optimized PostgreSQL queries, reducing end-to-end batch runtimes by 40%. Designed a layered Data Lake architecture (raw, staged, conformed) with Snowflake marts, reducing analyst data prep by 30%. Enabled governed self-service analytics with Power BI for 50 users and improved KPI visibility by 25%. Enforced HIPAA/PHI security with masking, RBAC, and Audit Logs; implemented automated Data Quality rules achieving 99% pipeline success; aligned data models to FHIR/HL7 and managed releases via JIRA with 99% SLA uptime.

Data Engineer at Capgemini

July 1, 2014 - November 30, 2017

Built end-to-end ETL pipelines using Informatica PowerCenter across 10+ source systems, processing ~5M records/day. Optimized SQL Server data models (T-SQL) and implemented SSIS data quality rules to reduce invalid records by 25%. Added structured error handling and 100+ API data validations using Selenium, Postman, and XML/JSON checks. Supported production deployments with monitoring, 99% SLA uptime, and controlled rollback procedures.