AI PlatformSep 2025 - Jul 2026

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.

3D Conversational Avatar Interface

Project Sheet & Impact

RoleLead AI & Software Architect
ClientLotoStudios
PeriodSep 2025 - Jul 2026
7
Real-Time Stages (Voice -> RAG -> 3D Avatar)
24/7
Autonomous Multilingual Concierge
Plug & Play
Drop-In Web Component for Any Website

Orchestration Pipeline

From the user's voice to the avatar's spoken reply, in a single low-latency real-time flow.

User Speech

User speaks to the avatar directly in the browser

Speech-to-Text

Real-time transcription of audio into text

Knowledge Retrieval (RAG)

Pulls verified answers from the client's continuously updated site content

LLM Reasoning

OpenAI crafts contextual replies and guides the conversation

Cloud Orchestration

High-concurrency, low-latency Node.js backend

Natural Voice (Polly)

AWS Polly turns the reply into natural speech

Live 3D Avatar

Drop-in web component on the client site: the 3D avatar speaks in lip-sync

Sample Conversation

User
What time does the hotel reception open?
Avatar
Reception is open 24/7. I can also help with early check-in or bookings - would you like me to proceed?

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

Node.jsOpenAI APIAmazon PollyAWS S3 / CloudFrontDockerCI/CD3D Assets

Key Contributions

01

Lead backend, integrations, AI services, and DevOps with end-to-end ownership of architecture, implementation, and deployment.

02

Design and maintain a modular Node.js integration layer deployable across websites with different tech stacks.

03

Built backend workflows for automated scraping, text chunking, embedding generation, retrieval logic, and dynamic speech synthesis.

04

Implemented voice generation workflows with Amazon Polly and managed multi-tenant asset delivery on AWS S3.

05

Operate CI/CD, environment configuration, and infrastructure optimization to support scalability and maintainability.

Get in Touch

Tell me about your project and I will get back to you fast. No fluff, no obligation.

Let's Discuss Your Project

Pick a time that works for you. We'll hop on a 30-minute discovery call to discuss your goals. There's absolutely zero obligation, and you'll receive free technical guidance regardless.

Chat on WhatsApp