---
title: SOF // SING
emoji: 🧠
colorFrom: indigo
colorTo: purple
sdk: static
pinned: false
---
---
## ENGINEERING INTELLIGENT SYSTEMS
I design and build software at the intersection of **Artificial Intelligence, LLMs, autonomous agents, backend engineering, infrastructure and cybersecurity**.
My work is focused on turning AI capabilities into **real operational systems** — systems that can reason over context, interact with tools, execute tasks, maintain state, validate results and recover from failure.
I approach AI as an engineering problem:
**model → architecture → execution → verification → reliability**
---
## WHAT I DO
|
### 🧠
**AI / LLM**
LLM Systems
Inference
RAG
Evaluation
Context Engineering
|
### 🤖
**AGENTS**
Tool Use
Planning
Memory
Orchestration
Autonomous Execution
|
### ⚙️
**ENGINEERING**
Python
FastAPI
AsyncIO
APIs
Linux
Databases
|
### 🛡️
**SECURITY**
Application Security
Network Security
Pentesting
Red Teaming
AI Security
|
## HOW I BUILD AI
01
UNDERSTAND
Context & Intent |
→ |
02
REASON
Planning & Decisions |
→ |
03
ACT
Tools & Execution |
→ |
04
VERIFY
Testing & Validation |
→ |
05
RECOVER
Failure Handling |
## CURRENTLY BUILDING TOWARD
**AUTONOMOUS CODING**
AI systems that understand repositories, modify code, execute tools and validate their own work.
**AGENT INFRASTRUCTURE**
Memory, context management, tool systems, orchestration and persistent execution.
**LOCAL AI**
LLM inference, model infrastructure and AI-powered development environments.
**AI RELIABILITY**
Evaluation, verification, failure analysis and recovery.
**AI SECURITY**
Security architecture for systems where intelligent models can access tools and infrastructure.
---
## THE DIFFERENCE
|
### MODEL
Intelligence
|
### SYSTEM
Intelligence + Tools + Execution
|
### PRODUCTION
System + Reliability + Security
|
**I build the layer between the model and production.**
## HUGGING FACE
This profile is my workspace for exploring and building around modern AI:
**MODELS · AGENTS · INFERENCE · EVALUATION · AUTOMATION · AI INFRASTRUCTURE**
