AI-Augmented Fullstack Signal & Backend Engineer

I bridge the gap between digital signal intelligence and robust system architectures. I build backend systems where state is explicit, persistence is practical, and workflows are augmented by multi-agent AI systems.

Go · Python · C++ · MATLAB · Gin · MongoDB · Wireless Systems

I don't just write code; I orchestrate it. My engineering workflow integrates:

• Multi-Agent Peer Consultation: Using independent AI systems (Claude/Gemini) for blind architectural review.
• Deterministic AI Workflows: Building self-healing tools with structured JSON schemas and verifiable paths.

• Modulation Recognition: Deep-learning workflows for real-time signal classification.
• Spectrum Semanticization: Transforming raw electromagnetic data into intelligent sensing workflows.
• Performance Analysis: NOMA user grouping and power allocation simulations.

Go Workflow Engine | DDD-Compliant | Dual-Persistence A production-grade task lifecycle backend. Featuring a hardened state machine, audit logging, and a repository-pattern-driven memory + mongo persistence layer for rapid DX and reliable deployment.

Meta-Engineering | Multi-Agent Skill | Deterministic AI A multi-agent consultation framework that collects independent, blind advice from multiple LLMs to minimize hallucination and solve complex architectural bottlenecks.

• Explicit State Semantics: Every transition must be verifiable.
• Practical Abstractions: Design for the 6-month-later-self (Low recovery cost).
• Security-First AI: Deterministic outputs via self-healing schemas.

• Website: asaqe.site
• Location: Xi'an, China