Generative AI Engineer

I am a Generative AI engineer and security researcher who builds LLM-powered products end to end. I work across the full stack, from prompting and agent design to deployment and operational hardening.

I focus on agentic systems, including MCP servers, AI agent tooling, and automation pipelines. I like building practical systems that help me and others work faster, with strong attention to reliability and security.

I operate with high agency and full ownership, and I am comfortable working independently as a founder and researcher. I have founded and led engineering work on my own projects while continuing to ship production-grade AI infrastructure.

My security research has been recognized through assigned CVEs, published GitHub Security Advisories, and resolved reports in programs at Amazon and AWS. I also participate in vulnerability research platforms such as HackerOne, Bugcrowd, YesWeHack, Amazon VRP, AWS VDP, and Vercel Open Source.

My technical background includes Python, C, Bash, low-level and assembly work, as well as security areas such as SSRF, authorization bypass, mobile and API security, kernel-level exploitation, and OT/ICS security. I also work with Linux, Cloudflare Tunnel, distributed systems, and API design.

I am currently building an AI automation company and a cyber-physical SOAR platform for smart-grid and energy infrastructure. I am especially interested in roles where I can combine generative AI, security, and systems engineering to deliver impactful products.