Ravikumar M. N.

Full-time · India

• Architecting a multi-agent assistant on LangGraph (specialized agents for retrieval, reasoning, and task execution) that holds sub-800ms average response latency across concurrent multi-tenant sessions and cut end-to-end task time 22%.
• Serve agents on Databricks Model Serving with Unity Catalog lineage and access control on every agent-facing source; Genie-based agents cut analyst query turnaround 30%.
• Built governance in from day one (model versioning, prompt and response auditing, access policies) plus Azure DevOps CI/CD that cut release cycle time 20% and deployment failures 15%.

Contract · India

• Designed and deployed an agentic RAG chatbot for enterprise knowledge, fed by Docling-based ingestion that turns unstructured documents into structured data.
• Built an agentic synthetic-persona generator for financial survey datasets to improve downstream model robustness and segmentation analysis.
• Ran the model lifecycle on Databricks, Azure, and MLflow: experiment tracking, versioning, and cloud deployment.

Full-time · Davangere, India

• Fine-tuned transformer NLP models from 78% to 89% sentiment accuracy while cutting inference latency 30%; custom classifiers raised pipeline accuracy 18% and cut processing time 25%.
• Built computer-vision pipelines for image classification and object detection with CNN and GAN models, reaching 92% accuracy.
• Designed a Gemini API–based extractor that turns unstructured healthcare documents into structured data in under 3 seconds, raising throughput 30%.

Internship · Remote, India

• Built AI services on FastAPI and AWS (EC2, S3, SageMaker) that cut generative-model inference response time from 5s to 2s.
• Integrated modular AI microservices with GPT-powered APIs into enterprise workflows, cutting manual content-creation time 40%.

A LangGraph assistant that retrieves, reasons, and acts across business workflows, with sub-800ms average responses and an audit trail on every turn.

<800ms average response latency · −22% end-to-end task time · −30% analyst query turnaround

One copilot over documents, tables, and analytics tools, with hybrid retrieval and query planning, answering in 1.8s end to end.

1.8s end-to-end response latency · <120ms vector search latency at scale

Docling parsing and LLM extraction turn PDFs, forms, and reports into JSON, a knowledge graph, and grounded QA, at under 3s per page.

<3s ingestion per page · 1.5s grounded QA response · +30% healthcare form throughput

Fine-tuning where prompting and retrieval run out, using SFT with LoRA, contrastive embeddings, and transformer classifiers taken from 78% to 89% accuracy.

89% sentiment accuracy, up from 78% · −30% inference latency · +10% F1 on imbalanced classes

Also built

• Agentic research automation. CrewAI agents that generate personas, run domain research, and compile structured reports. −50% manual research effort
• Conversational PDFs and websites. Turns static PDFs and sites into queryable knowledge systems. 95% query success rate
• Multimodal chatbot. Routes across three models to handle text and image interactions in one assistant. +35% user engagement
• Handwritten prescription → JSON. Structured extraction from handwritten medical prescriptions with Gemini Flash. <5s per prescription

IEEE student member; started the Enigma AI Club.