Software Developer
Arnav Panigrahi
Backend systems, full-stack applications, and AI/ML pipelines shipped to production.
Background
About
I build backend services, full-stack 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. Previously at Pinnacle Consulting, I built full-stack ERP systems and integrated geospatial services for a $75M utility provider.
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.
Experience
Where I've worked.
Software Developer
AllCheer- Built a LangChain AI agent for ROI workflows, automating authorization checks, compliance validation, and document generation while cutting processing time by 60% and saving $20K/year.
- Engineered a containerized FastAPI service that emulates authenticated RethinkBH sessions for real-time clinical record sync, bypassing 24-48-hour public API latency.
- Developed a React + FastAPI NER pipeline using OpenAI for structured data extraction from therapist notes at 92% accuracy.
Software Developer Intern
AllCheer- 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, moving Make.com prototypes into production service architecture.
Junior Software Developer
Pinnacle Consulting LLC- Integrated ArcGIS Online with Angular and .NET for a $75M utility provider, enabling real-time infrastructure visualization and reducing oversight errors by 30%.
- Delivered three full-stack ERP systems with Node.js and SQL Server, implementing JWT-based RBAC and complex query workflows to automate invoicing.
Capabilities
Tools I work with.
Languages & Frameworks
- Python
- TypeScript
- JavaScript
- C#
- .NET
- FastAPI
- React
- Angular
- Astro
AI & Data Systems
- LangChain
- LangGraph
- PyTorch
- Vector Search
- Embeddings
- Prompt Engineering
Infrastructure & Delivery
- Google Cloud
- Docker
- AWS
- REST APIs
- Node.js
- SQL Server
- PostgreSQL
- SQL
- Git
Selected Work
Projects
bedtime.ai
Extended a multi-modal AI storytelling system that turns children's drawings into narrated stories. The pipeline combines EfficientNet-B0 sketch classification (~70% accuracy on children's drawings), OpenAI GPT story generation, Coqui XTTS v2 voice cloning, and a touch-enabled React drawing canvas. Includes 35 backend tests, 19 frontend tests, and Docker Compose deployment.
- 4 models orchestrated in a single pipeline
- ~70% classification accuracy on children's drawings
- 35 backend + 19 frontend tests
Abliteration for LFM2.5
An interpretability study of 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.
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 coordination, KV-backed analytics, and a custom Vite markdown pipeline for blog content.
Yomiji
An offline-first WaniKani study app for Android, built with React Native and Expo. It implements secure API-token auth, SQLite-backed incremental sync with pending-write queues, dashboard, lesson, and review flows, romaji-to-kana answer checking, local search, diagnostics, and Jest-covered domain logic.
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.
LangChain RAG
A production-ready RAG pipeline for querying Star Wars scripts with LangChain, OpenAI embeddings, and Qdrant. Expanded from a tutorial into a configurable system with prompt-injection hardening, source attribution, ~30x cost reduction using GPT-4o-mini, and a 28-test suite.
View on GitHubEnterprise 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.