3D Conversational Avatar
Autonomous and intelligent 3D conversational virtual assistant. Developed for LotoStudios to innovate customer support.
Company context: Development of a scalable 3D conversational avatar platform for multi-client adoption.
1. RAG Ingestion
Automated scraping, vector embeddings, and RAG for a continuously updated, memory-aware knowledge base.
2. LLM Reasoning
OpenAI-driven reasoning engine to orchestrate contextual dialogues and dynamic real-time actions.
3. API & Backend
Scalable cloud-native architecture engineered with Node.js to handle high concurrency and async processing.
4. Web Delivery
Modular web component for seamless integration of the 3D avatar within any client website.
Infrastructure & Integrations
As the Backend AI Engineer for LotoStudios, I developed the entire intelligence layer and backend infrastructure from scratch. The main challenge was engineering a low-latency real-time experience, pairing LLM reasoning with user tracking, and orchestrating dynamically generated audiovisual streaming.
Tech & Infrastructure
Key Contributions
Lead backend, integrations, AI services, and DevOps with end-to-end ownership of architecture, implementation, and deployment.
Design and maintain a modular Node.js integration layer deployable across websites with different tech stacks.
Built backend workflows for automated scraping, text chunking, embedding generation, retrieval logic, and dynamic speech synthesis.
Implemented voice generation workflows with Amazon Polly and managed multi-tenant asset delivery on AWS S3.
Operate CI/CD, environment configuration, and infrastructure optimization to support scalability and maintainability.