Software Developer
Arnav Panigrahi
Building backend systems, fullstack applications, and AI/ML pipelines.
About
About
Backend, fullstack, and AI/ML -- with a focus on shipping.
Recent work includes RAG pipelines, LLM agents, REST APIs, and cloud deployments.
M.S. in Computer Science from UC Riverside.
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
bedtime.ai
A multi-modal AI storytelling system that turns children's drawings into narrated stories using EfficientNet-B0 for classification, Phi-3 or GPT for generation, and Coqui XTTS v2 for voice cloning.
- 4 models orchestrated in a single pipeline
- Image classification, story generation, voice output
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.
Nier Archive
A real-time collaborative site built with SvelteKit 5, Cloudflare Workers, Durable Objects, KV-backed analytics, and a custom Vite markdown pipeline.
Rethink BH Automation
A FastAPI service that syncs Rethink BH appointment and authorization data to Supabase in real time using authenticated API extraction.
LangChain RAG
A RAG pipeline using LangChain, OpenAI embeddings, and Qdrant for retrieval-augmented generation with prompt hardening, source attribution, and a full test suite.
View on GitHubEnterprise ROI System
An LLM agent that automates HIPAA document release workflows -- extracting, validating, and routing requests to reduce manual processing.