Renuka Sandati
Sr. Gen AI/ML Engineer | Prompt Engineer | Conversational AI | Expert in LLMs, RAG, LangChain & AWS Bedrock | Building Scalable AI Systems Across AWS, Azure & GCP | Healthcare Conversational AI | IBM Watsonx | LLMs, RAG
- Role
- Sr Gen Ai Engineer at Johnson & Johnson
- Location
- Waterbury, CT, US
- LinkedIn followers
- 500 followers
About Renuka Sandati
I’m a Senior Generative AI & Machine Learning Engineer specializing in Large Language Models (LLMs), Generative AI, RAG architectures, prompt engineering, and enterprise chatbots, with experience delivering AI solutions across healthcare, finance, and large-scale enterprise environments, including work with IBM platforms and ecosystems.I design and scale end-to-end AI and conversational AI platforms—from data ingestion and vector search to LLM fine-tuning, chatbot orchestration, and MLOps—leveraging AWS, Azure, GCP, IBM technologies, and tools such as SageMaker, Vertex AI, Azure ML, Bedrock, Databricks, Snowflake, Airflow, Kafka, and modern chatbot frameworks to drive secure, production-ready deployments.I’m deeply passionate about responsible AI, GenAI innovation, and intelligent chatbot adoption, helping enterprises integrate LLM-powered conversational systems and retrieval-based architectures for faster decisions, better user experiences, and measurable business impact. Always open to connecting with AI leaders, researchers, and teams advancing Generative AI, NLP, and ML engineering.
Experience
Sr Gen Ai Engineer
Jul 2023 — Present · NJ, US
As a Senior Generative AI Prompt Engineer, I design and optimize LLM-driven conversational AI solutions for regulated healthcare and enterprise environments, with a strong focus on prompt engineering, RAG architectures, and chatbot optimization. I develop and maintain reusable, HIPAA-compliant prompt libraries aligned with IBM Watson Assistant and watsonx frameworks to support intent classification, entity modeling, and policy-driven workflows across benefits, claims, and coverage use cases. By implementing prompt-centric retrieval-augmented generation with vector databases, I ground model responses in authoritative content to reduce hallucinations and improve response accuracy. I continuously refine prompts through A/B testing, conversation analytics, and SME feedback, improving intent resolution, lowering fallback rates, and ensuring enterprise AI governance, auditability, and PHI-safe design.
Education
Dhanekula Institute of Engineering & Technology
Bachelor of Technology - B.Tech, Computer Science
Find verified contacts for anyone on LinkedIn
Unifers gives sales teams verified emails and direct dials, enriched profiles, and outreach that lands in the inbox.
Free plan included · No credit card required
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.