Open to New-Grad Backend / AI Roles

New-grad backend / AI engineer building APIs, RAG systems, and observability-driven AI tools.

Experience building backend APIs, ML-backed workflows, RAG systems, and observability-driven AI tools—strong in Python, FastAPI, Node.js, PostgreSQL, and practical backend systems for AI products.

View selected workView resume
LinkedInGitHub

San Francisco Bay Area · Full-Stack · Applied AI · AI Systems & Agentic Governance · AI Product Design

Portrait of Shulabh Bhattarai

Shulabh Bhattarai

Backend · Applied AI · RAG

B.A. in Computer Science

Building

Fleetrac — AI governance platform (OpenTelemetry)

iOS + Android

Cross-platform MindMitra release

Now available on:

3

Engineers led as a student developer to build MindMitra

2

Ongoing research projects on Bio-Agro weapons

Work

Selected engineering projects

Selected engineering projects and case studies.

Mobile + Backend

MindMitra

Cognitive-wellness app (iOS + Android)

MindMitra (formerly CognizenX) is a cognitive-wellness app built with DePauw Neuroscience. I led a three-engineer team decoupling AI and data workflows from the shipped React Native client onto a dedicated Vercel/MongoDB backend—isolating ML updates from mobile release cycles while delivering iOS and Android builds with telemetry-driven spaced-repetition scheduling.

Role
Software Engineer – MindMitra
Core challenge
Take over a live v1 product under its prior CognizenX branding, decouple AI from the mobile client, expand to Android, and instrument telemetry for spaced-repetition research workflows without disrupting existing users.
  • Led 3 engineers migrating AI/backend off React Native; shipped iOS + Android updates.
  • 25-endpoint Vercel/MongoDB API centralizing auth, content generation, and scheduling.
  • GPT-4 pipeline: 3,000+ questions across 40+ subdomains, ~300K embedding dedup checks; 65 tests (~60% coverage).
  • React Native
  • Node.js
  • Express
  • MongoDB Atlas
  • GPT-4
  • Vercel

Previously released as CognizenX on the App Store; the product is now branded MindMitra.

Case study
Now available on:

Full-Stack + Applied AI

MediVise

Medical document RAG platform (capstone)

Built a secure, multi-tenant medical document RAG platform with FastAPI, Phi-4-mini, and Supabase/PostgreSQL—enforcing per-user authorization via Row-Level Security and optimizing retrieval with hybrid sparse/dense vectors and cached RxNorm lookups.

Role
Capstone Developer
Core challenge
Deliver a production-quality RAG backend for medical documents within a capstone scope—strict tenant isolation, controlled context windows, and bounded non-diagnostic AI outputs.
  • Multi-tenant Phi-4-mini ingestion API with Supabase RLS on PostgreSQL.
  • Hybrid sparse/dense search, token-aware chunking, and cached RxNorm lookups.
  • FastAPI
  • PostgreSQL
  • Supabase
  • Phi-4-mini

Educational prototype; not intended for diagnosis or medical advice.

Case study

AI Infra + Governance

Fleetrac

AI governance control plane

Building an AI governance platform that ingests OpenTelemetry traces, detects drift and policy violations across simulated agent systems, and drives approval-gated remediation through a FastAPI/SQLAlchemy backend and Next.js operator console.

Role
Independent Developer
Core challenge
Give operators a vendor-neutral way to detect, correlate, and remediate risky agent behavior from live telemetry—not just log dashboards.
  • OpenTelemetry governance platform across 10 simulated agent systems.
  • FastAPI/SQLAlchemy remediation with rolling 15-minute risk windows and approval-gated enforcement.
  • FastAPI
  • Next.js
  • SQLite
  • OpenTelemetry
Case study
View all work →

Experience

Engineering experience

Full 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).
  • React Native
  • Node.js
  • MongoDB Atlas
  • GPT-4
  • Jest
  • Supertest

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.
  • Django REST Framework
  • PostgreSQL
  • K-means
  • MLP
  • ETL

Engineering focus

Where I contribute

AI-first backend

FastAPI and Node.js services built around LLM pipelines, RAG, embeddings, inference endpoints, and telemetry—where AI workloads are first-class, not bolted onto CRUD.

Retrieval & data systems

Hybrid sparse/dense retrieval, vector stores, token-aware chunking, embedding deduplication, and PostgreSQL/MongoDB schemas tuned for AI-backed features.

Backend platforms

REST API design, authentication, ORM optimization, caching, ETL pipelines, ML model serving, and production integrations that keep AI services reliable.

Product delivery

React and React Native clients connected to backend AI features—from shipped mobile releases to capstone prototypes with bounded, responsible outputs.

LLM & agent tooling

  • OpenAI Agents SDK
  • Claude Agent SDK
  • LangGraph
  • MCP

Observability

  • OpenTelemetry
  • Langfuse

AI-assisted development

  • Cursor
  • Codex
  • Claude Code

Core stack

AI infra & retrieval

  • RAG
  • OpenAI APIs
  • pgvector
  • Ollama

Backend & data

  • FastAPI
  • Node.js
  • PostgreSQL
  • MongoDB
  • Supabase
  • Redis

Languages & delivery

  • Python
  • TypeScript
  • Docker
  • GitHub Actions

About

AI-first backend engineering

I build backend systems where LLM features, retrieval, and data pipelines are core to the architecture—not an afterthought layered on top of a generic API.

Recent work spans a GPT-4 content pipeline with embedding deduplication for MindMitra, multi-tenant RAG with Supabase RLS for MediVise, and ML model serving plus ETL pipelines from my internship at Togglecorp.

Read more about my approach →

Open to new-grad software engineering roles

Backend, full-stack, product engineering, and applied AI — where I can contribute to shipped systems.

Get in touchView resume

IBM SkillsBuild certifications: IBM AI Fundamentals · IBM Quantum Enigma