Arnav Panigrahi
Software Developer, AI/ML Enthusiast
Building ethical AI systems that solve real-world problems
About Me
I'm a Master of Science in Computer Science graduate from UC Riverside with 2+ years of professional software development experience specializing in Full-Stack development and AI/ML systems.
Currently, I'm working as a Software Developer at AllCheer, where I've reengineered HIPAA compliant enterprise systems achieving $20K annual savings and 60% faster processing times harnessing the power of AI and cloud infrastructure.
I'm passionate about responsible and ethical AI, privacy-respecting systems, and building technology that aligns with open-source values and user privacy principles.
My Skills
Backend Development & Infrastructure
- Python
- FastAPI
- Node.js
- Express.js
- Docker
- Kubernetes
Frontend Development & UI
- React.js
- Angular
- TypeScript
- JavaScript
- Tailwind CSS
- HTML/CSS
Machine Learning & AI
- PyTorch
- TensorFlow
- Scikit-learn
- LangChain
- LLMs
- RAG
Databases & Cloud
- PostgreSQL
- MongoDB
- Redis
- Google Cloud
- AWS
- Azure
Software Engineering
- Git
- CI/CD
- Agile
- TDD
- System Architecture
- Performance Optimization
My Projects
bedtime.ai – Multi-Modal AI Storytelling Platform
Developed an AI system that transforms children's drawings into personalized bedtime stories narrated in parents' voices. Integrated fine-tuned phi-3 LLM with computer vision (EfficientNet) and voice cloning for 30-second story generation. Built with React/Vite frontend, FastAPI backend, and containerized with Docker.
Rethink BH Automation – FastAPI + Cloud Run Backend
Built a production FastAPI service to sync real-time appointment and authorization data from Rethink BH to Supabase by emulating secure user login. Achieved 90% cost savings and reduced sync latency from 24-48h to real-time. Deployed with Docker, Secret Manager, and full observability stack on Google Cloud Platform.
RAG for Document Intelligence
Engineered a Retrieval-Augmented Generation system enabling semantic search across PDF datasets. Combined Pinecone for vector storage with Groq for inference, achieving 35% improved search relevance while maintaining sub-second response times. Implemented custom chunking strategies and comprehensive error handling.
Enterprise ROI System with AI Agent
Reengineered a manual Release of Information system to fully automate healthcare document workflow using an AI Agent. Streamlined the entire process resulting in $20K annual savings and 60% reduction in processing time. Built with enterprise-grade security and HIPAAcompliance standards.
Therapist Dashboard with GPT Integration
Developed an internal dashboard for 20+ therapists combining REST API CRM for schedule management and therapy progress tracking. Integrated GPT-powered API with custom prompts to structure unformatted input, achieving 35% higher performance compliance and 92% NLP accuracy.
ArcGIS Utility Mapping Solution
Integrated ArcGIS-based mapping solutions for a $75M/year revenue utility provider in North Carolina. Visualized electric pole installation and synced updates from field workers' mobile apps, reducing oversight error rate by 30%. Built with enterprise-grade security and real-time synchronization.