Skip to content

Software Developer

Arnav Panigrahi

Software developer building backend systems, fullstack applications, and AI/ML pipelines.

Arnav Panigrahi

About

What I work on.

I build across the stack -- backend services, fullstack applications, and AI/ML systems -- with a focus on getting things into production cleanly.

My recent work spans RAG pipelines and LLM agents, REST APIs and cloud deployments, and end-to-end web applications.

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

Clear systems and steady iteration.

Skills

Tools I use most.

Backend, fullstack, and AI/ML -- with a focus on production delivery.

Languages & Frameworks

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

AI & Data Systems

  • LangChain
  • LangGraph
  • PyTorch
  • Vector Search
  • Embeddings
  • Prompt Engineering

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

Nier Archive – Real-Time Collaborative Site

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 authenticated API extraction.

System ArchitectureFastAPICloud RunGoogle CloudDevOpsAutomation

LangChain RAG

Details

A RAG pipeline using LangChain, OpenAI embeddings, and Qdrant for retrieval-augmented generation with prompt hardening, source attribution, and a full test suite.

AI/MLLangChainVector SearchRAGLLMs

Enterprise ROI System with AI Agent

Details

An LLM agent that automates HIPAA document release workflows -- extracting, validating, and routing requests to reduce manual processing.

AI AgentEnterpriseAutomationLegal TechCost Optimization

Get in touch

Contact

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