Security Researcher Β· Software Engineer π Nairobi, Kenya (UTC+3)
Software engineer turned security researcher. 4+ years shipping production TypeScript, React and Node.js, now focused on how systems break: AI / LLM security, web app security and smart-contract auditing.
- π€ AI security - red-teaming LLM apps (Gray Swan arena), writeups and checklists mapping the OWASP LLM Top 10 and MITRE ATLAS onto real systems
- π© Top 1% on TryHackMe - SOC Level 1, Jr Penetration Tester, AI Security (path completed)
- β Smart-contract auditing - 10 CodeHawks First Flights, 1 medium-severity finding reported
- π‘οΈ Blue team - Splunk investigations, detection engineering, AD / Entra ID monitoring
- βοΈ Writing walkthroughs at sharonjebitok.com
π¨ Currently building: an LLM app recon toolkit (snapshot and diff a target's JS bundles, flag new endpoints)
πΌ Open to: security research, AppSec / AI security and security-minded engineering roles
| Project | What it is |
|---|---|
| ai-security-writeups | Pentest |
| reports from AI-security CTFs - 17 findings across prompt injection, SSRF, data poisoning | |
| and agentic trust-boundary bypass | |
| AI-Security-Checklists | OWASP |
| LLM Top 10, OWASP Top 10, MITRE ATLAS and STRIDE mapped to concrete checks, plus a | |
| prompt-injection payload library | |
| web3-auditing-projects | |
CodeHawks First Flight audits with a custom Foundry audit.sh (recon, Slither/Aderyn, |
|
| tests, pre-filled report) |
| π‘οΈ Security | π» Engineering | β Blockchain | βοΈ AI & cloud |
|---|---|---|---|
| Threat modelling, secure code review | TypeScript, React / Next.js, Node.js | Solidity, | |
| Foundry | LLM integration (OpenAI / Groq / Ollama) | ||
| Burp Suite, Nmap, Metasploit, Wireshark | Python, Rust, Bash, PowerShell | Slither, Aderyn | |
| AWS, Docker, Linux | |||
| Splunk, log & malware analysis, OSINT | Ruby on Rails, GraphQL | EVM, The Graph, ICP | Git |
| / GitLab CI |
π Portfolio β’ βοΈ Blog β’ πΌ LinkedIn β’ π§ Email




