aigen

Fullstack Engineer & Private AI Infrastructure Architect

I build enterprise-grade applications and deploy autonomous AI systems on private hardware. Unlike standard cloud wrappers, I utilize high-performance local inference stacks to ensure data privacy and zero dependency on external API costs. My workflow combines stable backend engineering with cutting-edge LLM orchestration (Qwen 3.x series).

High-Performance Infrastructure:

• Compute Power: Dual-GPU setup (RTX 5080 + RTX 3060, 64GB RAM) optimized for massive model inference.
• Model Expertise: specialized fine-tuning and running bleeding-edge models: Qwen 3.6/3.8 (27B, 35B A3B, Flash Next), Llama, and complex ComfyUI workflows.

Core Stack & Development:

• Engineering: Fullstack PHP (Symfony/Laravel) + JavaScript (React/Vue).
• DevOps: Docker ecosystem (Portainer/CLI), Advanced Linux Administration (Arch-based systems), Security automation.
• AI Engineering: Custom MCP servers, Voice Assistants, and Agent Skills generation.

I provide a "batteries-included" solution: I bring the hardware power to run 30B+ parameter models locally and the development skills to integrate them into your application seamlessly. Speed, privacy, and control are built into the architecture from day one.