.png){kind=logo}
Build offensive, agentic capabilities and customer-facing features using LLMs; design and ship production Python backends; lead technical design discussions; propose and implement roadmap initiatives; translate ambiguous challenges into actionable plans; uphold code quality and engineering standards while working with a fast-moving security product team.
About RunSybil
RunSybil is an AI security startup scaling offensive security services by automating hacker intuition. We’re building Sybil: an AI-powered penetration testing product that finds vulnerabilities faster than human hackers. Backed by strong investor support and early customer traction, our team is composed of experts from the likes of OpenAI, Meta, Mandiant, Palantir, Cruise, and Trail of Bits.
About this Role
We are seeking talented engineers intent on changing the security industry. If you have experience on fast-moving teams, building security products that developers love, and driving projects to completion through ambiguity: we want to talk to you.
Ideal candidates have experience building with LLMs.
What You’ll Do:
- Offensive agentic capability development
- End-to-end development of high-impact customer facing features and systems
- Propose and implement technical initiatives based on product roadmap needs
- Lead technical design discussions, contribute to team decisions, and provide feedback on engineering approaches
- Translate ambiguous technical challenges into actionable plans, and execute them in collaboration with the team
- Serve as the cornerstone of our engineering culture by setting and upholding exemplary standards for code quality, practices, and craftsmanship
We’re Looking For Someone Who Has A Mix of The Following:
- 4+ years of experience building software
- Offensive security experience finding vulnerabilities in a variety of targets
- Experience designing, deploying, and maintaining production Python backend code
- Strong understanding of modern JS, React, and Python design patterns
- Experience in writing testable and performant code
- Experience with generative AI: ideal candidates have built tools powered by an LLM
- Ideal candidates will be familiar with DevOps or infrastructure engineering concepts
- Seeks autonomy, creative problem-solving, and moving quickly
Location:
Hybrid role based in New York City. Some travel may be required.
What We Offer:
- Competitive Salary: Attractive startup compensation package with equity options
- Benefits: Excellent medical, dental, and vision plans. Unlimited PTO
- Growth Opportunities and Early Impact: Work directly with and learn from industry leaders while driving significant impact in our fast-growing security startup
We understand not every applicant will meet every qualification. We value hard work and potential, and still want to hear from you!
Similar Jobs
Artificial Intelligence • Blockchain • Professional Services • Security • Consulting • Cybersecurity • Defense
Conduct red-team assessments of formally verified systems, evaluating proofs, specifications, threat models, and trusted computing bases. Build AI-driven vulnerability discovery, triage, and exploit-generation tooling; identify and demonstrate exploitable weaknesses in software and infrastructure. Produce rigorous security reports, publish methodologies, collaborate with domain experts and third parties, and deliver engagements on fixed schedules.
Top Skills:
ButtercupC++DafnyF*FuzzingLeanPythonRocqRustSmtSymbolic ExecutionVerus
Cloud • Information Technology • Security • Software • Cybersecurity
Conduct AI security research, agentic and LLM testing, vulnerability discovery, adversary simulations, and full-chain red team operations. Test WAF, EDR, and SIEM detection efficacy using MITRE ATT&CK, collaborate with blue teams and incident response, develop detection validation frameworks, report risks to executives, and mentor security professionals.
Top Skills:
AIAutomated Breach And Attack SimulationAWSC2 InfrastructureCoding AgentsEdrGCPLlmsMitre Att&CkPrompt EngineeringSIEMWaf
Artificial Intelligence • Software
Design and validate threat models for agentic AI systems, create adversarial experiments and synthetic environments, develop static and dynamic risk analysis, fine-tune and evaluate models, and build production-ready guardrails, monitoring, dashboards, and evaluation infrastructure. Optimize security systems for latency, cost, reliability, and measurable real-world performance while translating research into product capabilities.
Top Skills:
Agentic AiDynamic AnalysisGenerative AiMachine LearningReinforcement LearningStatic Analysis
What you need to know about the NYC Tech Scene
As the undisputed financial capital of the world, New York City is an epicenter of startup funding activity. The city has a thriving fintech scene and is a major player in verticals ranging from AI to biotech, cybersecurity and digital media. It also has universities like NYU, Columbia and Cornell Tech attracting students and researchers from across the globe, providing the ecosystem with a constant influx of world-class talent. And its East Coast location and three international airports make it a perfect spot for European companies establishing a foothold in the United States.
Key Facts About NYC Tech
- Number of Tech Workers: 549,200; 6% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: Capgemini, Bloomberg, IBM, Spotify
- Key Industries: Artificial intelligence, Fintech
- Funding Landscape: $25.5 billion in venture capital funding in 2024 (Pitchbook)
- Notable Investors: Greycroft, Thrive Capital, Union Square Ventures, FirstMark Capital, Tiger Global Management, Tribeca Venture Partners, Insight Partners, Two Sigma Ventures
- Research Centers and Universities: Columbia University, New York University, Fordham University, CUNY, AI Now Institute, Flatiron Institute, C.N. Yang Institute for Theoretical Physics, NASA Space Radiation Laboratory
