Bhargavi Kurukunda
AI / ML Engineer · MS CS, UCSB

Bhargavi Kurukunda

Agents, ranking models, and full-stack products, shipped and tested, not just demoed.

Skills
Gen AI
LLM APIs (Claude, Gemini, Groq) MCP Agent Orchestration Prompt Engineering RAG Vector Retrieval
Machine Learning
PyTorch scikit-learn XGBoost SHAP CNNs VLMs
Languages & Tools
Python TypeScript React Node.js SQL FastAPI REST API C++
Backend & Data
Supabase PostgreSQL SQLite Redis AWS Docker GitHub Actions Grafana
Projects
demo
01 · HackerRank Orchestrate
AgentsVision

WhatsApp Message Notification Router

Deterministic rules for the obvious cases, confidence-gated LLM escalation for everything ambiguous. Text, image, and voice, unified into one pipeline.

96.7% accuracy 0 failures
View code ↗
demo
02 · Personal Project
MLAgents

ML Stock Ranking & Insights MCP

XGBoost ranking model evaluated on chronologically split data to eliminate lookahead bias. Rankings and SHAP explanations exposed as MCP tools an LLM can call directly.

chronological split SHAP-grounded
View code ↗
demo
03 · Personal Project · Solo
Full-Stack

Rhyme

Full-stack writing platform, designed, built, and shipped solo. React and TypeScript frontend, Supabase backend, Stripe subscriptions, plus an MCP server for live production data queries.

550+ paying users solo-built
demo
04 · Slack Agent Builder Challenge
Agents

TaskLoop

Turns meeting transcripts into owner-tagged action items, every task backed by a verbatim source quote. Rebuilt around async queues to beat Slack's 3-second response window.

3s ack time zero-invention
View code ↗
demo
05 · Prompt-Driven Development Hackathon
Conversational AIAgents

Verbatim

Real-time multilingual interpreter for patient-clinician conversations. Five coordinated agents (Intake Conductor, Follow-up Proposer, Coverage Tracker, Red-Flag Monitor, History Scribe) in a shared Band.ai room.

Top 3 finish 5-agent coordination
View code ↗
demo
06 · MS Thesis · with UT Austin
Research

IoTSim

Declarative DSL and compiler generating pseudo-realistic IoT sensor streams with causal event chains, for training downstream ML models at production scale.

~30K events/sec 1.03 scaling exponent 1.85M events
View code ↗
demo
07 · Personal Project · Solo
VisionFull-Stack

FrameVision

Form a frame with both hands, thumb and index fingers, and the interior live-restyles through an AI video model. Real-time hand tracking (MediaPipe) compositing a live Decart video stream, fully client-side.

real-time hand tracking live AI video restyle
View code ↗
demo
08 · Personal Project · Solo
MLFull-Stack

MotionStitch

Assembles Bharatanatyam dance compositions synced to a song's beat structure: audio phrasing analysis, pose extraction from reference performances, and a Three.js 3D avatar rendering the composed choreography live.

beat-synced composition 3D pose rendering
View code ↗

Let's build something real.

Open to new grad AI/ML, backend, and full-stack roles.