Felixai
Event-driven platform syncing and processing Canvas LMS content. Apache Kafka pipelines for large-scale ingestion, OCR, and AI workflows; Server-Sent Events for real-time sync progress; tuned for I/O-bound performance.
AI & Backend Engineer
I build LLM systems, RAG pipelines, and the scalable backends behind them.
Remote · Canada
Remote · Singapore
Remote · United States
Remote · Germany
Event-driven platform syncing and processing Canvas LMS content. Apache Kafka pipelines for large-scale ingestion, OCR, and AI workflows; Server-Sent Events for real-time sync progress; tuned for I/O-bound performance.
Outbound voice-calling agent built with Vapi. Real-time STT/TTS pipelines for natural dialogue, with dynamic prompt logic and external tool integration for scenario-based workflows.
Multi-tenant Zendesk-style support SaaS. Scalable WebSocket chat with Redis-backed sessions, hybrid PostgreSQL + MongoDB storage, and subscription-based access control.
Efficient vector store using a K-means tree over SQLite. Cluster-based search, full scans, and Random Projection dimensionality reduction for fast retrieval.
FastAPI + Azure OpenAI service that extracts structured data (order/PO/registration numbers) from .eml files and attachments, cross-verified against a PostgreSQL inventory DB.
AI ad-automation for Facebook/Google Ads. Content generation backend with image/video models, Facebook Graph API auto-posting, ESRGAN enhancement, and an OpenCV video pipeline.
RAG-based document tool processing 100–700 page PDFs, generating structured documents for civil engineers with extracted insights and reference links.
A from-scratch automatic differentiation engine in C++ for efficient gradient computation.