Giorgi G.
Offer Giorgi work on your next project.
Rating
Skills and abilities
Programming
Design & art
Photo, Audio & Video
Mobile development
Outsourcing & consulting
Portfolio
-
3300 USD Low-Latency AI Voice Agent for real-time call processing
Enterprise Resource Planning (ERP)Developed a voice AI agent for automatic handling of incoming calls, customer consultations, and transferring requests to an operator.
The system operated on a realtime pipeline:
… Call → STT → AI Logic → TTS → voice response to the client
What was implemented:
— telephony / SIP integration;
— real-time speech recognition;
— AI dialogue logic and intent processing;
— voice response generation via TTS;
— minimization of delay between replies;
— scenarios for transferring to an operator;
— dialogue history preservation;
— integration with CRM / Telegram / API;
— notifications to managers about new requests.
Special attention was given to:
— minimal response delay;
— naturalness of dialogue;
— stable operation during calls;
— handling client interruptions;
— fallback scenarios;
— quality control of responses.
Result:
— AI agent responds to clients without an operator;
— reduced workload on managers;
— calls are automatically classified;
— requests are sent to CRM/Telegram;
— the system is ready for scaling to multiple lines.
Technologies:
Python / Node.js, SIP / WebRTC, STT, TTS, LLM, WebSockets, Redis, CRM API, Telegram API
-
5000 USD High-performance Backend in Go for a real-time application system
Databases & SQLDeveloped a backend system in Go for processing requests, events, and notifications in real-time.
The service was designed for high load, minimal latency, and stable operation in production.
… What was implemented:
— REST API for the client interface;
— WebSocket server for real-time updates;
— event queue and handlers;
— application status system;
— user roles and access;
— integration with external APIs;
— logging, monitoring, and health-checks;
— Docker deployment on Linux/VPS.
Special attention was paid to:
— clean architecture;
— request processing speed;
— fault tolerance;
— scalability;
— API security.
Results:
— backend reliably processes thousands of events;
— real-time updates arrive without delays;
— the system is ready for scaling;
— reduced load on manual process handling.
Technologies:
Go, PostgreSQL, Redis, WebSockets, REST API, Docker, Linux, Nginx
-
4500 USD AI system for automating Telegram sales and client communications
AI & Machine LearningDeveloped an AI-driven platform for automating communication with clients via Telegram, including AI bots, request processing, notifications, real-time statuses, and automated interaction scenarios.
The system included:
— Telegram bots for clients and operators;
… — AI processing of incoming messages;
— automatic request distribution;
— real-time notifications and statuses;
— integrations with CRM/API;
— analytics and monitoring system;
— automation pipelines for handling client scenarios.
Special attention was given to:
— response speed;
— fault tolerance;
— low-latency architecture;
— scalability;
— stable operation under high load.
Results:
— significant reduction in manual workload for operators;
— acceleration of request processing;
— automation of routine communications;
— stable operation of real-time infrastructure;
— system readiness for scaling.
Technologies:
Node.js, Go, Telegram API, WebSockets, Redis, PostgreSQL, Docker, AI Integrations
-
3500 USD High-load SQL system for Telegram Gifts (10M+ records)
Databases & SQLDeveloped and optimized a high-performance SQL architecture for storing, searching, and analyzing Telegram gifts with over 10 million records.
The system was designed for minimal latency and high load:
— optimized complex JOIN and SELECT queries;
… — implemented indexing and partitioning;
— integrated caching via Redis;
— configured replication and monitoring;
— optimized real-time data update pipelines.
Results:
— stable operation under high load;
— minimal query latency;
— 99.99% uptime;
— processing thousands of requests per second;
— readiness for further scaling.
Technologies:
PostgreSQL, Redis, Docker, Linux, Go, Real-Time Processing