# Pranitha Chilvari

> Data Scientist | AI/ML Engineer | RAG | LLM | AWS | Kubernetes | Docker | AWS | Power BI | NLP |

Location: United States, United States
Profile: https://flows.cv/pranitha

I’ve never seen the role of a Data Scientist or AI/ML Engineer as just a job. I see it as a responsibility, because the systems I build directly influence business decisions and outcomes. Choosing this path wasn’t by chance it was a deliberate decision driven by my interest in data, AI, and their ability to improve how organizations operate and grow.

I take full ownership of the solutions I develop, focusing not only on making them work, but on ensuring they deliver measurable value to stakeholders. Data and AI are not side interests for me they shape how I think, solve problems, and approach my work.

My journey began with exposure to different business functions, including digital marketing and accounting. What became clear to me early on was that data sits at the center of every decision. I was consistently drawn to understanding problems deeply and asking how data could be used to make processes more effective. That curiosity and problem-solving mindset led me to pursue data science and AI/ML.

Today, I apply that same mindset to solving complex, enterprise-scale challenges. I believe in being disciplined, patient, and consistent in execution. I take ownership of outcomes, value clear communication, and focus on building trust with both technical and business stakeholders. Experience has taught me that meaningful progress takes effort, persistence, and a commitment to continuously raising the bar.

## Work Experience
### AI/ML Engineer @ Wells Fargo
Jan 2025 – Present | United States
Designed and delivered a GenAI-powered platform to automatically generate clear, consistent, and audit-ready decision narratives for high volume banking operations, including fraud investigations, transaction disputes, and customer complaints.

Built secure AWS-based data pipelines to ingest structured case evidence and implemented a Retrieval-Augmented Generation (RAG) architecture to ground narrative generation in historical precedents, standardized templates, and case-specific facts. Designed controlled, multi-agent reasoning workflows to validate evidence, reconstruct timelines, synthesize decision rationales, and enforce narrative consistency.

Deployed scalable GenAI services with robust monitoring, hallucination safeguards, and compliance controls, significantly reducing manual narrative preparation time and improving audit response turnaround for risk and operations teams

### Machine Learning Engineer @ athenahealth
Jan 2022 – Jan 2023
Designed and deployed a machine learning–driven readmission risk scoring platform to predict 30-day hospital readmissions and support proactive post-discharge care planning.

Built end-to-end ML pipelines on Azure to ingest, validate, and preprocess large scale clinical and operational data, engineering clinically meaningful features such as prior utilization patterns, comorbidity indices, and discharge risk indicators. Developed and productionized a Gradient Boosting based classification model, achieving significant improvement in high-risk patient identification over rule-based baselines.

Deployed the model as a scalable inference service on Azure Kubernetes Service (AKS) with full CI/CD automation, experiment tracking, and monitoring for data drift and performance degradation. Model insights were operationalized with clinical and care coordination teams, contributing to measurable reductions in avoidable readmissions in pilot hospital units.

### Data Scientist @ adidas
Jan 2021 – Jan 2022
Designed and delivered a large-scale pricing and promotion analytics platform to evaluate the true business impact of discounts, bundles, and markdowns across regions, stores, and product categories.

Built scalable ELT pipelines on Google Cloud to process 10M+ monthly retail transactions from POS systems, pricing engines, and promotion calendars. Developed analytical data models and KPI frameworks to measure promotion uplift, incremental revenue, margin dilution, and ROI with accurate pre-, during-, and post-promotion attribution.

Performed exploratory data analysis to uncover price elasticity patterns, promotion cannibalization, and region-specific responses. Created executive-level dashboards in Looker and automated reporting for merchandising and finance teams, enabling data-driven pricing decisions and measurable improvements in promotion ROI while reducing margin leakage.

### Associate Data Scientist @ MetLife
Jan 2020 – Jan 2020
Built an enterprise analytics platform for policy servicing and claims operations, processing 100M+ records annually. Developed Python-based ETL pipelines, analytical data models, KPI layers, and Power BI dashboards to track SLA adherence, claim settlement efficiency, and operational bottlenecks, contributing to faster decision-making and improved claims turnaround.


## Education
### Master's degree in Information Science
University of Arizona

### Bachelor of Technology - BTech in Computer Science
Jawaharlal Nehru Technological University


## Contact & Social
- LinkedIn: https://linkedin.com/in/pranitha-chilvari-7b6168221

---
Source: https://flows.cv/pranitha
JSON Resume: https://flows.cv/pranitha/resume.json
Last updated: 2026-04-17