Vetted Retrieval-Augmented Generation (RAG) Professionals

“Backend engineer who built and scaled AmazonProAI, a multi-tenant SaaS platform for Amazon sellers, using a modular Django/DRF monolith with strict seller-level isolation and security controls. Led a controlled SQLite-to-PostgreSQL migration and hardened bulk Excel ingestion with idempotency and data integrity constraints to prevent duplicate metrics and noisy alerts while keeping the system ready for future service extraction.”

“Full-stack developer who has built both operational software for universities and an AI-assisted publishing platform called HeartThreads. Notably implemented a multi-LLM fallback architecture using Ollama, OpenAI, and Claude to keep AI story-generation features available in production.”

“Backend-focused developer who built LinguaTile (language learning app) on a FastAPI + MongoDB monolith deployed to Google Cloud Run, emphasizing async performance and security (RBAC/JWT, rate limiting, request tracing). Also created Mark-RS, a static HTML generator with a 100% CommonMark-compliant Markdown parser, demonstrating strong edge-case rigor and systems robustness.”

“Built FlowPilot, an AI-powered product that generates complete importable n8n workflows from natural-language prompts using a RAG pipeline (Qdrant + LangChain) and a multi-stage agent with a scoring/repair 'Judge' loop for intent alignment. Experienced in backend architecture across Laravel/Node microservices and production AI/RAG systems, plus performance debugging from async job offloading to database index tuning after ORM migrations.”

Anjali Chepuri

Screened

“Built and deployed an LLM-powered financial document processing and summarization platform at Morgan Stanley using a production RAG pipeline (PDF ingestion, embedding-based retrieval, schema-constrained JSON outputs) delivered via FastAPI microservices on Kubernetes. Drove measurable impact (40% reduction in manual review time) and improved factual accuracy for numeric fields by 30% through metadata-aware retrieval, strict schemas, and post-generation validation, with a human feedback loop from financial analysts.”

“Built multiple AI projects end-to-end as a solo developer, including a privacy-focused LLM app that redacts PII before sending prompts to an external model and a LangGraph-based multi-agent triage system for log analysis. Stands out for combining LLM/agent design, deployment troubleshooting, and practical workflow automation with a strong emphasis on privacy and explainability.”