Skip to content

Software Developer

Arnav Panigrahi

Software developer building backend systems, AI products, and reliable infrastructure.

Arnav Panigrahi

About

What I work on.

I build software that moves data reliably, reduces manual work, and stays understandable as requirements change.

Most of my recent work has focused on backend services, AI workflows, and infrastructure.

I hold a master's degree in computer science from the University of California, Riverside.

What I optimize for

Simple interfaces, reliable pipelines, and maintainable implementation.

How I work

Small decisions, clear systems, and steady iteration.

Skills

Tools I use most.

Strongest in backend systems, AI workflows, and production delivery.

Languages & Frameworks

  • Python
  • TypeScript
  • JavaScript
  • C#
  • .NET
  • FastAPI
  • React
  • Astro

AI & Data Systems

  • LangChain
  • LangGraph
  • RAG Pipelines
  • PyTorch
  • LLMs
  • Vector Search

Infrastructure & Delivery

  • Google Cloud
  • Docker
  • AWS
  • REST APIs
  • PostgreSQL
  • SQL
  • Git

Selected Work

Projects that reflect how I work.

A mix of public projects, research, and production systems with real operational constraints.

Abliteration for LFM2.5

An interpretability project for LiquidAI/LFM2.5-1.2B-Instruct focused on refusal directions, weight orthogonalization, and inference-time intervention using manual PyTorch hooks.

ResearchLLM InterpretabilityPyTorchHugging Face

Edge-Native Real-Time Web Platform

A real-time collaborative site built with SvelteKit 5, Cloudflare Workers, Durable Objects, KV-backed analytics, and a custom Vite markdown pipeline.

SvelteKit 5Cloudflare WorkersDurable ObjectsWebSockets

More Work

Additional projects.

Rethink BH Automation – FastAPI + Cloud Run Backend

Details

A FastAPI service that syncs Rethink BH appointment and authorization data to Supabase in real time using secure login emulation.

System ArchitectureFastAPICloud RunGoogle CloudDevOpsAutomation

RAG for Document Intelligence

Details

A RAG system for semantic search over PDFs using Pinecone, Groq, and custom chunking for faster and more relevant retrieval.

System DesignAI/MLVector SearchRAGPerformance Optimization

Enterprise ROI System with AI Agent

Details

An AI-driven system for Release of Information workflows that automates the document lifecycle under HIPAA requirements.

AI AgentEnterpriseAutomationLegal TechCost Optimization

Get in touch

Contact

Open to software engineering, platform, and applied AI roles.