Software Developer

Arnav Panigrahi

Backend systems, fullstack applications, and AI/ML pipelines -- shipped to production.

Portrait of Arnav Panigrahi

Background

About

I build backend services, fullstack applications, and AI/ML pipelines with a focus on shipping reliable software to production. My work spans FastAPI microservices on Google Cloud, LangChain-based AI agents for enterprise workflows, and multi-modal ML systems combining computer vision, NLP, and voice synthesis.

At AllCheer, I've delivered measurable impact -- a 60% reduction in document processing time, $20K in annual cost savings, and 92% accuracy on an NER pipeline for clinical data extraction. I thrive at the intersection of backend engineering and applied AI, where system design meets real-world constraints.

I hold an M.S. in Computer Science from UC Riverside, where I focused on distributed systems and machine learning. I'm currently seeking software engineering roles in backend systems and applied AI.

Based in California, United States
Education M.S. Computer Science, UC Riverside

Experience

Where I've worked.

Software Developer

AllCheer
California, USA Mar 2025 - Present
  • Built a LangChain AI agent automating ROI processing -- authorization checks, compliance validation, and document generation -- cutting processing time by 60% and saving $20K/year.
  • Engineered a containerized FastAPI service emulating authenticated RethinkBH sessions for real-time clinical record sync, bypassing 24-48hr public API latency.
  • Developed a React + FastAPI NER pipeline with OpenAI for structured data extraction from therapist notes at 92% accuracy.

Software Developer Intern

AllCheer
California, USA Jun 2024 - Dec 2024
  • Designed a Python logistics engine on Google Cloud with Google Maps APIs for multi-stop route optimization and large-scale staff scheduling.
  • Led backend R&D and API schema design for ROI automation, prototyping in Make.com and translating to production service architecture.

Capabilities

Tools I use most.

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

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. Reduced model refusal rate from 50% to ~37% without retraining.

PyTorch / Interpretability / Research
View on GitHub

Nier Archive

A real-time collaborative site with live cursor sharing and viewer presence, built with SvelteKit 5, Cloudflare Workers, Durable Objects for stateful WebSocket connections, KV-backed analytics, and a custom Vite markdown pipeline for blog content.

SvelteKit / Cloudflare / WebSockets
View on GitHub
Rethink BH Automation

A containerized FastAPI service deployed on Google Cloud Run that emulates authenticated user sessions against RethinkBH endpoints to sync appointment and authorization data in real time, bypassing 24-48 hour API latency for downstream applications.

FastAPI / Cloud Run / Automation
LangChain RAG

A production-ready RAG pipeline querying Star Wars scripts using LangChain, OpenAI embeddings, and Qdrant. Rebuilt from a tutorial with configurable data sources, prompt hardening against injection, source attribution, ~30x cost reduction (GPT-4o-mini), and a 28-test suite (13 mocked unit + 15 integration).

RAG / LangChain / Qdrant
View on GitHub
Enterprise ROI System

An LLM agent that automates HIPAA document release workflows -- orchestrating authorization checks, compliance validation, and document generation to reduce manual processing time by 60% and deliver $20K in annual savings.

AI Agent / Automation / HIPAA

Get in touch

Contact

Currently seeking software engineering roles in backend systems and applied AI. Let's talk.