Navya Sree Yellina

Generative AI Engineer | ML Architect | Innovation Catalyst

🚀 Turning AI dreams into reality, one algorithm at a time. I don't just build AI systems—I craft intelligent experiences that understand, adapt, and amaze. From architecting RAG frameworks that boosted accuracy by 25% to reducing latency from a coffee break (2.1s) to a heartbeat (1.26s), I transform data into decisions and complexity into clarity. Fresh M.Sc. graduate (May 2025) with a thesis on Privacy Threats in Continuous Learning, now bringing cutting-edge AI solutions to life at Gemini Consulting. Ready to revolutionize how your business thinks? Let's chat!

Saint Louis, MO
4+ Years Experience
Generative AI & LLMsTransformers (GPT, BERT, T5)RAG FrameworksMLOps & CI/CDPrivacy-Preserving MLDeep Learning & PyTorch
Get In Touch

Featured Projects

Showcasing enterprise-scale AI solutions with measurable impact

Enterprise Generative AI Platform

Gemini Consulting & ServicesGenerative AI Engineer

Architected enterprise generative AI platform using OpenAI GPT API, transformers, and deep learning models with PyTorch and TensorFlow, reducing information retrieval latency by 40% (2.1s → 1.26s) while supporting 500+ concurrent users.

Key Results

Latency Reduction40%
Concurrent Users500+
NLP Accuracy25%

Technologies

PythonPyTorchTensorFlowOpenAI GPT APILangChainFastAPI
View Case Study

Multi-Channel AI Contact Center

Gemini Consulting & ServicesGenerative AI Engineer

Deployed multi-channel AI agents using Python, Azure APIs, and MLOps best practices for contact center operations, increasing response throughput 30% (450→585 requests/min) with focus on ethical AI principles.

Key Results

Throughput Increase30%
Deployment Speed35%
Error Reduction80%

Technologies

PythonAzure APIsMLOpsDockerKubernetesAWS SageMaker
View Case Study

ML Monitoring System for Microservices

Oracle CernerSystems Engineer

Built distributed machine learning monitoring system using Python and deep learning frameworks for 50+ microservices, reducing incident response time by 20% while maintaining 99.9% uptime across 2.5M+ daily transactions.

Key Results

Response Time-20%
System Uptime99.9%
Cost Savings$50K

Technologies

PythonTensorFlowZabbixDockerKubernetesAWS
View Case Study

Let's Connect

Whether you're looking for a Gen AI expert, need consultation, or want to discuss research collaboration, I'd love to hear from you.

Availability

Available for immediate joining
Visa Status: F1 OPT
Response time: Within 24 hours

Interested in:

  • •Generative AI Roles
  • •MLOps Positions
  • •Freelance/Consulting Projects
  • •Research Contributions/Collaborations