Diwash Bhandari

Building production-grade backends, RAG platforms, and multi-tenant SaaS systems. 5+ years shipping APIs that handle 100K+ requests/day with sub-200ms response times.

Backend engineer focused on scalable system architecture, AI/ML integration, and production DevOps. I design high-performance APIs, orchestrate RAG pipelines, and build platforms that handle real-world traffic — from 10K to 100K+ concurrent users with 99.9% uptime.

• RAG Orchestration Platform — 7-step semantic pipeline (chunking → embedding → search → generation → streaming), 92% accuracy across 10K+ enterprise documents with real-time SSE monitoring
• AI Fitness Coach — Multi-platform (Telegram/Discord) conversational AI with 14+ LLM providers, automatic failover, and zero-hallucination guardrails
• Enterprise SaaS Tooling — Multi-tenant architecture, tenant isolation, and performance optimization at scale

Backend:    Python · FastAPI · Django · Starlette · SQLAlchemy · asyncpg
AI/ML:      LangChain · LiteLLM · OpenAI · Anthropic · ChromaDB · Qdrant
Databases:  PostgreSQL · Redis · MongoDB · Vector Stores · Elasticsearch
Infra:      Docker · Kubernetes · AWS · GCP · GitHub Actions · Terraform
Frontend:   React · Next.js · TypeScript · Tailwind CSS · WebSockets
Languages:  Python · Go · TypeScript · JavaScript · PHP
Tools:      Pytest · Ruff · Pyright · UV · Temporal · GraphQL

RAG Orchestration Platform FastAPI · LangChain · ChromaDB · WebSockets 7-step semantic pipeline, 92% accuracy, sub-2s response, 7+ vector DBs supported → Code · → Demo

Gym Fitness Coach Bot FastAPI · LiteLLM · Discord.py · aiogram 14+ LLM providers with automatic failover, zero-hallucination guardrails, 9 database tables → Code

IntelliDocs AI FastAPI · LangChain · ChromaDB · OpenAI 92% accuracy, 10K+ docs processed, 60% latency reduction via WebSocket streaming → Code · → Demo

ResearchGen SaaS FastAPI · Multi-Model AI · Docker No-code AI research assistant builder — deploy custom assistants in under 5 minutes → Code · → Demo

• Building Reliable Background Workflows with Temporal and FastAPI: A Step-by-Step Guide (Apr 1, 2026)
• Build AI Apps on the Edge: A Step-by-Step Guide to Cloudflare Workers AI with Python & GLM-4.7-Flash (Mar 31, 2026)
• You Accidentally Pushed Your .env File to GitHub — Here's How to Actually Fix It (2026 Guide) (Mar 22, 2026)
• The 2026 Golden Path: Building and Publishing Python Packages with a Single Tool (uv) (Feb 9, 2026)
• Context Engineering: The Next Evolution Beyond Prompt Engineering (Jan 12, 2026)

— Automatically updated via GitHub Actions from Medium