← Back to notebook

Vaibhav R. Dandala

ML Engineer · AI Researcher · Research Engineer

vrdandal@ncsu.edu·(984) 244-8318·github.com/VaibhavD2006·linkedin.com/in/vaibhav-dandala

Education

North Carolina State University

B.S. Electrical Engineering & Computer Engineering (Dual Degree)

Concentrations: Machine Learning & AI · Computer Systems Software

Raleigh, NC

Expected Dec 2028

GPA: 3.80

Experience

UNC Department of Radiation Oncology

Lead Machine Learning Engineer

Chapel Hill, NC

Apr 2026 – Present

  • Achieved 93% accuracy on vertebrae segmentation and lesion detection by co-developing a CNN pipeline combining MedSAM3 for segmentation and YOLOv8 for detection, trained on 65,000+ CT images.
  • Reduced radiologist data prep time by 35% across active clinical trials by building segmentation and preprocessing pipelines, directly accelerating oncology research throughput.

NASA Jet Propulsion Laboratory

AI/ML Researcher

Remote

Jun 2025 – Feb 2026

  • Built RAG pipeline using PineconeDB with hybrid BM25 + dense embeddings; 80%+ PDS3 filter prediction accuracy across MSL archives.
  • Processed and indexed 10,000+ MSL mission records across structured and unstructured PDS3 archives, enabling planetary scientists to query decades of Mars rover data through a natural language interface for the first time.

Defense Advanced Research Projects Agency (DARPA)

ML Engineer Intern

Remote

Apr 2025 – Jul 2025

  • Deployed real-time edge ML on IoT for pose estimation and object detection in military zones; built synthetic data + quantization pipeline for battlefield hardware evaluation.
  • Engineered annotation workflows across 3,500+ synthetic and real-world battlefield frames, directly improving model reliability for soldier-deployed edge hardware under strict compute constraints.

HavenSmart LLC

AI Developer & Team Lead

Remote

Apr 2024 – Jun 2024

  • Deployed internal RAG chatbot (LangChain, PineconeDB, Docker) handling 5,000+ monthly employee queries on deployment processes and workflows.
  • Eliminated 60% of manual onboarding overhead for engineering hires by replacing live CI/CD and architecture walkthroughs with a vector-search pipeline over internal NetApp docs.

Publications

LUMIN — Agentic LLM Multimodal NASA PDS Query System

ICMLA 2025 · Co-authored with Dr. Emily Dunkel, NASA Jet Propulsion Laboratory

Projects

KeyMailkey-mail.co

SaaS · Agents

AI-native CRM and marketing automation platform for realtors. Agentic inbox, campaign sequences, and LinkedIn/X marketing. Built Key Moments — a pg_cron-scheduled milestone engine that invokes Claude with pgvector RAG to generate personalized drafts, with approval-gated agentic writes and immutable per-event audit traces.

Next.jsReactSupabasePostgreSQLpgvectorGemini

NASA / LUMINPaper

RAG · Research

Agentic LLM multimodal query system over NASA's Planetary Data System (PDS) archives. Enables natural language queries over 10,000+ Mars Science Laboratory mission records. Co-authored with JPL Lead Data Scientist Dr. Emily Dunkel; published at ICMLA 2025.

PythonPineconeDBBM25Dense EmbeddingsFastAPILangChain

CaseForge AI

SaaS · AI

AI-powered consulting case interview prep platform. Provides adaptive mock interviews with 7-dimension scoring and readiness dashboard for candidates targeting MBB/T2 firms like McKinsey, BCG, Bain.

Next.js 16TypeScriptTailwind CSSGoogle GeminiOllamaPostgreSQL

Skills & Tools

ML/AI

PyTorchCNNsYOLOv8MedSAM3Computer VisionMCPQuantizationModel Fine-tuning

LLM & RAG

LangChainAgentic Self-Loop OrchestrationHybrid BM25 + Dense RetrievalOpenAIGeminiPineconeDBpgvector

Systems & Dev

PythonJavaScriptFastAPINext.jsDockerAWSSupabaseMongoDBPostgreSQLGitCI/CD