HarshJannawar
Security and AI security engineer based in San Francisco, open to remote or hybrid roles and relocation, with experience shipping production systems and red-teaming agentic AI systems.
Skills
Domains
Show original post
Location: San Francisco, CA Remote: Yes (remote or hybrid) | Relocate: Yes (SF Bay Area, Seattle, NYC, Austin, other US hubs) Technologies: Python, security engineering, agentic AI and MCP security, LLM red-teaming, guardrails, threat modeling, DevSecOps, AWS, Docker, Next.js, Node.js, AI security Résumé: https://www.harshjannawar.com/resume | github.com/Harshj143 | [email protected] What I’m proudest of is taking a startup from zero to a live production platform with 20+ paying customers within 3 months, built entirely from the ground up: product development, secure SDLC, full-stack delivery, and the AWS infrastructure to run it daily. Inline Proxy is my open source MCP security gateway: it enforces allow/block/redact/approve policy on every agent tool call and blocks a full prompt-injection exfiltration chain without ever needing to detect the injection itself. On the offensive side, I designed and ran a prompt injection payload against a Claude Opus 4.8 email triage agent in a controlled lab, achieving successful injection in 8 of 10 attempts while the agent still completed its legitimate task in all 10. I also cleared all 3 escalating levels of Trajectory Labs’ Terminal red team assessment against a hardened PARALLAX agent, including a ticket authority spoof that triggered a privileged password reset. Trajectory Labs’ lab work has found vulnerabilities across Opus 5.5, Fable, Mythos, Gemini, and Argon. MS in Cybersecurity Engineering (UW), thesis became AegisLLM, an OWASP LLM Top 10 red team suite using a genetic algorithm to evolve attacks: github.com/Harshj143/AegisLLM. Top 1% TryHackMe, CTF win at UWB GreyHats. Looking for security engineering or AI security roles at companies putting agents in production.
Top job matches
10ThreatMark
Brno
ThreatMark is hiring for multiple full-time security and ML engineering roles, including backend, DevOps, DevSecOps, AI tech lead, security research, fraud detection, and partner management, with remote worldwide options and Brno, Czech Republic.
GovStar
Remote
GovStar is hiring a Security Engineer and a Data Engineer for remote U.S.-based work supporting national security missions.
Curai
Remote
Curai is hiring senior software engineers for remote US full-time roles building AI-powered healthcare experiences, agent workflows, and evaluation systems.
Meta
Bellevue, Menlo Park, New York, Washington DC
Meta is hiring Senior/Staff Security Engineers for Central Security to work on AI and native-code security, vulnerability research, assessments, and internal security/privacy initiatives.
FusionAuth
Denver
FusionAuth is hiring Senior/Staff Java Engineers and an Account Executive for authentication/authorization products, with remote Europe-only and onsite Denver roles.
SadServers
Remote
SadServers is hiring a remote software engineer in Canada for part-time or contract work to build SRE AI evaluation/training products using Django, Python, and React.
Radar Labs
NYC
Radar Labs is hiring software engineers across multiple disciplines for a full-time remote-friendly US role based in NYC.
Scento
Paris
Scento is hiring multiple full-time roles in Paris/Berlin with remote work available in the EU, including engineering, data, product, growth, SEO, and CRM positions.
getregistered
Remote
Seeking an experienced remote DevOps freelancer to manage and enhance a GCP, Terraform, and GitLab stack in a SOC2/PCI environment.
Rootly
Remote
Rootly is hiring across engineering, product, GTM, and sales for roles focused on on-call, incident response, and AI SRE.