platform with GPT + LangChain pipelines for parsing

Location: Australia (open to any time zone) Remote: Yes Willing to relocate: No Technologies: Python, TypeScript, React/Next.js, LangChain, GPT-4/Claude/Mistral, RAG, FastAPI, AWS (Lambda/S3/DynamoDB), Postgres, Redis, Docker, Kubernetes, Swift/SwiftUI Senior full-stack + applied-AI engineer. I take ideas to production without supervision. Recent shipped work: - EventConnectHQ (freelance, solo): designed full system architecture and shipped a production MVP in 3 months — backend, REST APIs, modular React frontend, CI/CD, post-launch monitoring - Workzen: architected an AI hiring platform with GPT + LangChain pipelines for parsing, scoring, and multi-step orchestration. Integrated ATS, calendar, email, Slack via REST + webhooks - Production RAG knowledge engine: vector indexing (Pinecone/FAISS), intelligent caching, low-latency semantic search across large unstructured corpora - Aether: peer-to-peer iOS mesh app — multi-hop flood routing, store-and-forward, push-to-talk audio (Swift, SwiftUI, MultipeerConnectivity) - Hurricane: terminal-based AI coding assistant with modular execution pipelines and iterative refinement loops Best fit: AI-product teams that need someone to own an LLM feature end-to-end (prompts → evals → RAG → deploy → monitor), or founders who need a 90-day MVP shipped without a team. Available: 20+ hrs/week, contract or contract-to-hire. Email: i.lathifshaik@gmail.com GitHub: github.com/lathifshaik LinkedIn: linkedin.com/in/lathifdev