Red Teamer
Simbian
IndiaremotePosted 16 days ago
Skill Required
Red-TeamerPenetration-TesterSecurity-ResearcherEthical-HackerOffensive-Security-EngineerRed-Team-OperatorRed-Team-ExpertRed-Team-SpecialistRed-TeamRed-Team-ResearcherRed-TeamingRed-Team-EngineerRed-Team-ConsultantRed-Team-CybersecurityPenetration TestingEngineeringautomationsecuritybuildingTestNGOWASPCloudGenerative AIandAIMachine LearningFulltime
Key highlights
- 3-6 years experience in offensive security
- Competitive comp + equity
- Remote-first, async-friendly culture
- Focus on building an autonomous AI pentesting agent
Role overview
Simbian AI is building the world's first autonomous AI security agent that thinks, hunts, and responds like a seasoned security analyst. They are currently developing an AI pentesting agent that autonomously probes, exploits, and reports vulnerabilities across modern infrastructure, seeking a Red Teamer to serve as the adversarial brain behind the product. This is not a role for running red team engagements; instead, you will be the expert who makes AI agents think and act like skilled attackers, turning deep hands-on attack expertise into AI-powered products.
Responsibilities
- Be the offensive security brain behind our AI agents - defining how they reason, plan, and execute across attack scenarios
- Translate attacker methodology into structured workflows the AI can learn from and act on
- Cover the breadth of offensive security: network and web pentesting, phishing and social engineering, cloud and infrastructure attacks, adversary emulation, threat intelligence
- Validate product output against what a skilled human attacker would actually do - close the gap when the AI falls short
- Research emerging techniques across the offensive security landscape and get them into the product
- Work closely with engineering to improve agent accuracy, realism, and coverage
- Document attack logic, edge cases, and findings in ways that feed back into the product
Requirements
- 3-6 years in offensive security, red teaming, or penetration testing
- Strong offensive security background across multiple domains: web, network, cloud, social engineering, or adversary simulation
- Real-world experience: pentesting, bug bounty, red team engagements, CTFs, or security research
- Ability to break complex attack chains into structured, repeatable steps
- Someone who thinks in attacker TTPs, not just tools
- Curiosity about AI and genuine interest in building with it, not just using it
Nice to have
- Experience with LLMs, agentic systems, MITRE ATT&CK, or security automation
- Working knowledge of prompt injection, jailbreaking techniques, and OWASP Top 10 for LLMs
- CEH, OSCP, or equivalent - preferred, not required
- Experience red teaming agentic AI systems or multi-agent pipelines
- Background in threat intelligence or APT simulation
- Contributions to bug bounty programs (AI/ML targets a plus)
- Familiarity with AI safety and alignment concepts
Benefits
- Work on a problem most security teams haven't even defined yet
- Direct impact on product - your findings shape what we build
- Remote-first, async-friendly culture
- Competitive comp + equity at an early-stage AI security company
- Work alongside people who've shipped security products at sc
Additional details
- Most red teamers execute campaigns. Here, you build the agent that runs them. Your expertise becomes the product - and scales beyond what any single person could do alone.
- Originally posted on Himalayas