MANAV SINGH J. — AI Researcher
AI Security Engineer specializing in LLM vulnerabilities and autonomous security systems. I find security flaws in AI systems before attackers do — and build agents that automate the hunt. 🎯 PROOF OF WORK - Top 1% globally in Gandalf AI Red Teaming CTF (achieved Level 8 — only elite researchers reach this) - Active HackerOne researcher with AI vulnerability discoveries under review: → Prompt Injection in Notion AI enabling workspace data exfiltration → SSRF in Ollama API allowing cloud metadata access - Improved AWS CIS compliance 26% at Paytm (62% → 88%) through Python automation - Identified 8+ OWASP Top 10 vulnerabilities in production fintech APIs - Oracle OCI Generative AI Professional certified (2025) - IEEE YESIST12 global finalist for AI innovation 🔧 WHAT I BUILD Akagami — An autonomous pentesting agent using Claude's Model Context Protocol (MCP) - Reads codebases, identifies vulnerabilities, suggests patches automatically - Tested on 15+ open-source projects - Reduces manual security testing time by 40% Currently researching: AI agent security, LLM red teaming techniques, micrograd internals 💼 EXPERIENCE Enterprise security at Paytm (fintech, millions of users) - API penetration testing with Burp Suite Professional - Cloud security automation (AWS IAM, S3, Security Hub) - Data Loss Prevention assessments (30% risk reduction) 🛠️ TECH STACK AI Security: Prompt Injection, OWASP LLM Top 10, MITRE ATLAS, PyRIT Offensive: Burp Suite Pro, Metasploit, Nmap, SSRF, XSS, SQLi Cloud: AWS (IAM, S3, CIS Benchmarks), Azure (learning), Docker Development: Python, JavaScript, FastAPI, Model Context Protocol (MCP) 📍 OPEN TO - AI Security Engineer roles (remote/hybrid) - Security research collaborations - AI product security consulting - Speaking at security conferences 💬 LET'S CONNECT IF YOU'RE - Building AI products that need red teaming - Researching LLM security or AI agents - Hiring for AI security roles - Working on autonomous security systems 📧 manavsinghjamwal@gmail.com 🔗 GitHub: github.com/jamwal69
Stackforce AI infers this person is a Cybersecurity expert specializing in AI security and vulnerability assessment.
Location: Jammu, Jammu & Kashmir, India
Experience: 11 mos
Skills
- Ai Security
- Vulnerability Assessment
- Cybersecurity
- Machine Learning
Career Highlights
- Top 1% globally in Gandalf AI Red Teaming CTF
- Identified critical vulnerabilities in major AI systems
- Improved AWS CIS compliance by 26% at Paytm
Work Experience
Self-Employed / Open Source
Security Researcher (11 mos)
Paytm
Cybersecurity Audit Intern (10 mos)
Model Institute of Engineering and Technology
Centre for Research Innovation & Entrepreneurship (CRIE Labs) (4 mos)
Nucleon - Plan for a better tomorrow
Blockchain Intern (1 mo)
Education
Computer science engeenering at Model Institute of Engineering and Technology
Bachelor of Engineering at Model Institute of Engineering and Technology
