Programming Languages
Python Java C++ SQL JavaScript Bash / Shell
AI & Machine Learning
LLM RAG Semantic Search LlamaIndex Qdrant Agno Agent Transformers Prompt Eng.
Frameworks & Libraries
FastAPI Flask NumPy Pandas Scikit-learn Matplotlib
Core Engineering
Operating Systems DBMS Computer Networks System Design REST APIs
Specialized Domains
Data Science Data Analytics Software Development NLP Computer Vision
Tools & DevOps
Git Docker Scrum / Jira VS Code Postman Linux
AI Engineering Intern
May 2025 – July 2025
Antz AI Internship

At Antz AI, I operated at the frontier of applied AI engineering — designing and deploying production-grade Retrieval-Augmented Generation (RAG) pipelines that bridge large language models with domain-specific knowledge bases. Working across the full AI stack, I integrated vector databases for high-throughput semantic search, implemented semantic chunking strategies to improve retrieval precision, and conducted systematic benchmarking to ensure low-latency, hallucination-resistant outputs ready for real-world deployment.

End-to-End RAG Pipelines Vector DB Integration Semantic Search AI Workflow Testing Performance Optimization Scalable Deployment
Accepted for Publication
Retrieval-grounded Multimodal Clinical Language Modeling
ICTIS 2026  ·  Springer LNNS
Primary Author  —  Sudhakar K S

This research proposes a retrieval-grounded multimodal framework to address hallucinations in clinical LLMs. By unifying structured clinical text with imaging-derived contextual features, the framework ensures secure, offline, and verifiable language generation. It supports privacy-preserving deployment in resource-limited clinical settings, demonstrating high semantic consistency between retrieved evidence and generated outputs.

RAG Clinical LLM Multimodal Hallucination Mitigation Privacy-Preserving AI