Shulabh Bhattarai

Backend / AI Engineer

New grad software engineer with experience building backend APIs, ML-backed workflows, RAG systems, and observability-driven AI tools. Strong in Python, FastAPI, Node.js, PostgreSQL, and building practical backend systems for AI products.

San Francisco, CA
925-877-8163

Technical skills

AI / Retrieval: RAG, OpenAI APIs, Embeddings, Hybrid Retrieval, Ollama, OpenTelemetry
Backend / APIs: FastAPI, Node.js, Express, Django REST Framework, SQLAlchemy, REST APIs
Databases / Caching: PostgreSQL, MongoDB Atlas, Supabase, Redis, SQLite
DevOps / Cloud: Docker, GitHub Actions, Vercel, Git, CI/CD
Languages: Python, TypeScript, JavaScript, SQL

Work experience

Software Engineer – MindMitra

DePauw Neuroscience Department · Greencastle, IN

  • Led a 3-engineer team to migrate AI and data workflows from a shipped React Native app into a dedicated backend architecture, enabling independent backend releases and faster iteration on ML-powered features.
  • Built and maintained a 25-endpoint Node.js/Express backend on Vercel and MongoDB Atlas to centralize authentication, AI content generation, and scheduling workflows behind a unified API layer.
  • Developed an automated GPT-4 content pipeline that generated 3,000+ questions across 40+ subdomains and ran ~300,000 embedding-based similarity checks to enforce semantic deduplication.
  • Improved backend security and maintainability by moving exposed AI credentials server-side, implementing rate limiting and request validation, and expanding test coverage to 65 automated tests (~60% coverage).

Software Engineering Intern

Togglecorp · Kathmandu, Nepal

  • Optimized PostgreSQL-backed Django REST APIs by eliminating N+1 ORM bottlenecks with select_related, prefetch_related, and composite indexing, reducing analytics payload latency across 200K+ records.
  • Integrated K-means and MLP models into the Django serving layer, handling model serialization and batched inference for customer segmentation and demand forecasting endpoints.
  • Built memory-efficient ETL pipelines for behavioral transaction data using idempotent transformations and vectorized aggregations to support downstream recommendation systems.

Projects

Fleetrac — AI Governance Control Plane

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

  • Built an AI governance platform that ingests OpenTelemetry traces to detect behavioral drift, prompt-injection risk, and tool-scope violations across 10 simulated agent systems.
  • Developed a FastAPI/SQLAlchemy remediation workflow that correlates risk events, escalates incidents in rolling 15-minute windows, and supports approval-gated policy enforcement and post-action verification.

MediVise — Medical Document RAG Platform

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

  • Built a secure multi-tenant document ingestion API using Phi-4-mini, isolating user vectors and metadata with Supabase Row-Level Security over PostgreSQL.
  • Improved retrieval quality with hybrid sparse/dense search, token-aware chunking, and caching for RxNorm lookups to reduce external API latency.

Education

B.A. Computer Science

DePauw University, IN

  • Honors: Cum Laude, Computer Science Honors Award
  • Leadership: Co-founder & President, DePauw AI Club