Raghu Reddy Gayam
Ai Ml Engineer @UnitedHealth Group
Signup · Get unlimited contacts
WORK HISTORY
Ai Ml Engineer @UnitedHealth Group
Engineered ML models for claims classification & fraud detection, improving triage accuracy by 26% and reducing financial leakage. Automated claims adjudication with FastAPI on AWS Lambda, cutting latency 35% and accelerating reimbursements. Built NLP pipelines for ICD/CPT mapping & EOB parsing, reducing denials & billing errors. Designed & deployed LLM-powered RAG pipelines for claims queries, lowering support costs & improving SLA compliance. Fine-tuned GPT & LLaMA models on healthcare financial data, improving contextual accuracy in reimbursement summaries & compliance reporting. Developed chat/voice bots leveraging Azure AI & App Services, enhancing provider/patient interactions. Applied responsible AI principles (bias checks, explainability dashboards, compliance audits) to ensure ethical deployment. Working knowledge of AI agents using LangChain and OpenAI GPT-4 to automate patient support queries, improving response time by 40% and enhancing user experience. Built Power BI & Seaborn dashboards to monitor claims costs, fraud risk & model drift for proactive decision-making. Conducted evaluations of emerging AI tools (semantic search, vector DBs, prompt engineering frameworks) to maintain innovation. Mentored junior engineers and contributed to AI/ML knowledge-sharing initiatives within the organisation.
EDUCATION
Kennesaw State University
Master's degree
Veltech Dr.RR Dr.SR University
Bachelor of Technology - BTech
ABOUT RAGHU REDDY GAYAM
AI/ML Engineer with 5 years of experience building and deploying machine learning and NLP systems in healthcare and fintech domains. I specialize in designing production-ready ML pipelines, real-time inference APIs, and generative AI applications using Python, TensorFlow, AWS, FastAPI, and Hugging Face. I’ve applied deep learning, LLMs, and MLOps to solve real-world problems — from improving fraud detection by 30% to automating patient support with AI agents, cutting response times by 40%. I have hands-on expertise in fine-tuning GPT/LLaMA models, building RAG pipelines, and deploying AI agents using LangChain, LlamaIndex, and AutoGen. Experienced with scalable model deployment using AWS Lambda, SageMaker, and Kubernetes (EKS), and developing ML monitoring dashboards. I am passionate about GenAI and driving automation through intelligent agents, with a strong foundation in Python, SQL, and cloud-native ML architectures.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.