Shulabh Bhattarai

DePauw Neuroscience Department · Greencastle, IN

• Took technical ownership of a shipped React Native cognitive-wellness app, leading a three-engineer team in moving AI and data workflows from the mobile client to an independently deployed backend while delivering updated iOS and Android builds.
• Architected and deployed a 25+ endpoint Node.js/Express API on Vercel with MongoDB Atlas, centralizing authentication, AI quiz content generation, personalized learning state, and quiz performance telemetry.
• Built an automated demand-aware GPT-4 content pipeline that identifies question-bank gaps across 43 subdomains and applies embedding-based semantic deduplication before persistence.
• Remediated exposed client-side credentials by migrating AI operations server-side; added session authentication, Joi validation, tiered rate limits, and 57 automated tests across 18 Jest/Supertest suites.

Togglecorp · Kathmandu, Nepal

• Optimized Django REST Framework and PostgreSQL analytics over 200K+ consumer records across five regions through targeted indexing, query restructuring, and reduced response payloads.
• Implemented backend filtering and aggregation workflows that converted behavioral and transaction data into regional and spending-tier datasets consumed by an interactive React and Chart.js dashboard.
• Prototyped customer segmentation and sales-forecasting pipelines using K-means and a lightweight multilayer perceptron, formatting model outputs for dashboard evaluation across targeting, recommendation, and demand-planning use cases.

FastAPI, Next.js, SQLite, OpenTelemetry · Independent Project · 2026 – Present

• Built a vendor-neutral telemetry pipeline that ingests runtime events from OpenTelemetry, AWS Bedrock, Azure OpenAI, and Vertex AI, normalizing provider payloads before rule-based detection, incident correlation, evidence packaging, and remediation guidance.
• Developed a closed-loop workflow across 10 simulated agent systems, connecting live telemetry to owner queues, evidence packages, approval-gated remediation, notifications, and post-action verification through a FastAPI backend and Next.js operator console.

FastAPI, PostgreSQL, Supabase, RAG · Capstone Project · Aug 2025 – Nov 2025

• Built a FastAPI document-ingestion and RAG backend using Phi-4-mini, enforcing per-user authorization across uploaded documents and metadata stored through Supabase/PostgreSQL.
• Implemented hybrid semantic and keyword retrieval with configurable chunking to control retrieved context size, and cached RxNorm and geocoding lookups to reduce redundant external API calls.

DePauw University, IN

• Honors: Cum Laude, Computer Science Honors Award
• Leadership: Co-founder & President, DePauw AI Club
• Certifications: IBM AI Fundamentals | IBM Quantum Enigmas