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

I am an AI/GenAI Engineer based in Cary, NC with over 4 years of experience building production-grade GenAI systems across insurance and healthcare. I specialize in agentic orchestration, retrieval-augmented generation, and end-to-end LLM deployment, and I enjoy turning complex requirements into scalable, observable solutions that deliver measurable business impact. In my work, I design multi-agent systems, integrate external APIs and document services, and build robust MLOps pipelines to ensure reliable, compliant, and efficient AI products. I’m passionate about practical AI that improves decision-making, speeds up operations, and unlocks value for users and stakeholders.…I am an AI/GenAI Engineer based in Cary, NC with over 4 years of experience building production-grade GenAI systems across insurance and healthcare. I specialize in agentic orchestration, retrieval-augmented generation, and end-to-end LLM deployment, and I enjoy turning complex requirements into scalable, observable solutions that deliver measurable business impact. In my work, I design multi-agent systems, integrate external APIs and document services, and build robust MLOps pipelines to ensure reliable, compliant, and efficient AI products. I’m passionate about practical AI that improves decision-making, speeds up operations, and unlocks value for users and stakeholders.

Saran Kumar Reddy Palle

Data Scientist, AI Developer, Full Stack Developer, +2





I am an AI/GenAI Engineer based in Cary, NC with over 4 years of experience building production-grade GenAI systems across insurance and healthcare. I specialize in agentic orchestration, retrieval-augmented generation, and end-to-end LLM deployment, and I enjoy turning complex requirements into scalable, observable solutions that deliver measurable business impact. In my work, I design multi-agent systems, integrate external APIs and document services, and build robust MLOps pipelines to ensure reliable, compliant, and efficient AI products. I’m passionate about practical AI that improves decision-making, speeds up operations, and unlocks value for users and stakeholders.…I am an AI/GenAI Engineer based in Cary, NC with over 4 years of experience building production-grade GenAI systems across insurance and healthcare. I specialize in agentic orchestration, retrieval-augmented generation, and end-to-end LLM deployment, and I enjoy turning complex requirements into scalable, observable solutions that deliver measurable business impact. In my work, I design multi-agent systems, integrate external APIs and document services, and build robust MLOps pipelines to ensure reliable, compliant, and efficient AI products. I’m passionate about practical AI that improves decision-making, speeds up operations, and unlocks value for users and stakeholders.

Available to hire

I am an AI/GenAI Engineer based in Cary, NC with over 4 years of experience building production-grade GenAI systems across insurance and healthcare. I specialize in agentic orchestration, retrieval-augmented generation, and end-to-end LLM deployment, and I enjoy turning complex requirements into scalable, observable solutions that deliver measurable business impact.

In my work, I design multi-agent systems, integrate external APIs and document services, and build robust MLOps pipelines to ensure reliable, compliant, and efficient AI products. I’m passionate about practical AI that improves decision-making, speeds up operations, and unlocks value for users and stakeholders.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Work Experience

AI Engineer at MetLife

February 1, 2025 - Present

Architected and deployed a production-grade GenAI auto-adjudication system that automated medical insurance utilization review and enabled straight-through processing for standard claims. Achieved a 99% reduction in claim processing time (5 days to under 1 hour) and cut adjudication cost from $40 to $10 per claim, delivering $2M+ in annualized savings within 6 months. Implemented a Docker-containerized multi-agent system with agentic orchestration (LangGraph/StateGraph) enabling parallel execution across 50+ threads. Built MCP (Model Context Protocol) plug-and-play interfaces for external APIs, databases, and document services to improve scalability and context consistency. Integrated METIQ (proprietary LLM) with context injection and deterministic prompts to improve medical reasoning. Leveraged Azure Document Intelligence for OCR/layout analysis and Azure Language for medical entity extraction and PII redaction. Established an end-to-end LLMOps and observability stack with LangSmith f

AI Engineer Intern (Co-op) at Acentrik Technology Solutions

August 1, 2024 - December 1, 2024

Built a production-grade RAG system over 10,000+ internal articles with sub-2s latency and 95%+ faithfulness, validated via a RAGAS evaluation pipeline. Implemented Redis semantic caching to bypass the LLM for 40% of repeat queries, reducing response latency by ~1.5 seconds. Deployed a high-concurrency generative AI backbone on AWS Bedrock with LangChain to orchestrate Llama 3 (70B) at enterprise scale. Engineered a hybrid search and reranking architecture (BM25 + dense vector) using Reciprocal Rank Fusion and cross-encoders, increasing retrieval precision by ~30% for complex technical intent.

Data Scientist at Accenture (Client: Sanofi)

October 1, 2020 - July 1, 2023

Built and deployed predictive ML/DL models (Scikit-Learn, TensorFlow, PyTorch) for healthcare use cases (patient outcomes, treatment effectiveness). Developed NLP pipelines for unstructured clinical text with automated preprocessing, validation, and monitoring on scalable AWS/Azure pipelines, improving data quality and real-time inference. Implemented end-to-end AI/ML solutions with CI/CD (GitHub Actions) and MLflow for reproducible deployments, along with monitoring and governance pipelines.