Skip to content
DEV Community

DEV Community

[画像:MxGuru profile picture]

MxGuru Subscriber

AI security engineer focused on how LLMs fail — prompt injection, jailbreaks, and agent behaviour. I build systems that stress, break, and harden AI under real-world conditions.

Location Australia ,Queensland Joined Joined on Personal website https://sovereignhive.com.au/ github website

Education

Self Taught

Work

Sovereign Hive

Badges

Gemma 4 Challenge Completion
Hermes Agent Challenge Winner
1 Week Community Wellness Streak
Writing Debut

Skills/Languages

Python, TypeScript, Bash | LLM systems (vLLM, Ollama, llama.cpp) | Prompt injection & jailbreaks | AI red teaming | Agentic systems | Quantisation, LoRA/qLoRA | Local-first AI infra

Currently learning

Breaking and hardening AI systems — prompt injection, jailbreaks, and agent behaviour. Building defences that hold when models act autonomously.

Currently hacking on

Breaking and hardening AI systems — prompt injection, jailbreaks, and agent behaviour. Building defences that hold when models act autonomously.

Available for

Say hey if you're working on AI systems that break — prompt injection, agent behaviour, red teaming, or building defences that actually hold in real-world use.

Post 18 posts published
Comment 3 comments written
Tag 15 tags followed

Want to connect with MxGuru?

Create an account to connect with MxGuru. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
loading...
DEV Community

We're a place where coders share, stay up-to-date and grow their careers.

Log in Create account

AltStyle によって変換されたページ (->オリジナル) /