We are building the Runtime Authorization Engine for AI Agents — authorization infrastructure for autonomous software that operates in real-world contexts, requiring evaluation of actions based on content, context, and risk.
This is an early-stage, wide-scope role. You will work directly with the three founders, have real influence over what gets built, and be involved from core engineering through to customer delivery.
The Role
Your work spans two areas:
Product Development
- Design integrations with agent runtimes and models (Claude Code, Cursor, OpenAI Codex, and others)
- Ensure compatibility with agent frameworks including Google ADK, Langchain, and N8N
- Develop core authorization services for tool call policy decisions
- Own full-stack implementation from authorization logic to DevOps
- Apply expertise in identity management, RBAC/ABAC models, and cryptographic security primitives
Customer Delivery
- Lead technical deployments within enterprise customer environments
- Consult on complex authorization and agent security architecture
- Translate customer feedback directly into roadmap improvements
- Bridge engineering and go-to-market by being the technical voice in sales conversations
What We're Looking For
- 2–6 years of hands-on software engineering experience
- Full-stack development and modern cloud deployment knowledge
- Working understanding of agent runtimes and the LLM ecosystem
- Self-directed — you operate well with minimal oversight and make sound decisions independently
- Demonstrated output matters more than formal credentials
- Prior experience as a high-performing freelancer or self-directed OSS contributor is a major plus
What We Offer
- Competitive salary benchmarked against top European startups
- Stock options as a core component of the compensation package
- Direct access to founders and customers from day one
- The chance to define authorization infrastructure for a category that doesn't fully exist yet
How We Hire
No referrals or academic records required. Our selection process focuses entirely on actual work samples and practical assignments that reflect the real demands of the role.