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.
Education
Self Taught
Work
Sovereign Hive
Badges
Gemma 4 Challenge Completion
Awarded for completing the Gemma 4 Challenge. Thank you for participating! 💻
Hermes Agent Challenge Winner
Awarded for winning the Hermes Agent Challenge 🏆
1 Week Community Wellness Streak
For actively engaging with the community by posting at least 2 comments in a single week.
Writing Debut
Awarded for writing and sharing your first DEV post! Continue sharing your work to earn the 4 Week Writing Streak Badge.
GitHub Repositories
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.
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.