Yashwanth Reddy
Ai Engineer @Jp Morgan Chase & Co
Signup · Get unlimited contacts
WORK HISTORY
Ai Engineer @Jp Morgan Chase & Co
US
Designed and deployed scalable AI inference platforms using Docker, Kubernetes, and AWS EC2 GPU clusters, enabling60K+ real-time inferences/ day, achieving 99.8% uptime and reducing model latency by 35% for enterprise analyticsworkloads.Built multimodal LLM pipelines with LangChain, OpenAI API, and PyTorch to support anomaly detection and RAG-basedinsights, improving detection accuracy by 31% and accelerating data triage across high-volume transactional andtelemetry streams.Productionized AI microservices via FastAPI, MLflow, and Airflow, collaborating with platform, DevOps, and dataengineering teams to standardize CI/ CD pipelines and reduce deployment timelines by 50%.Implemented model optimization and monitoring using TensorRT, Prometheus, and Grafana, increasing GPU utilizationby 28% while enabling real-time observability across distributed inference endpoints.Mentored junior engineers and partnered with data science teams to transition research models into production, cuttingprototype-to-production cycles from 2 weeks to 5 days and increasing business adoption.
EDUCATION
New Jersey Institute of Technology
Master's degree, Data Science
ABOUT YASHWANTH REDDY
Aspiring for a challenging position in an Organization which provides me an opportunity to show my talent, improve my skills and knowledge for benefit and growth of self and the organization.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.