About the Role
We are building a world model for cybersecurity, starting with threat modeling. Our system autonomously models attack paths, validates them, and remediates vulnerabilities.
Responsibilities
- Wire up MCP servers shared across agent swarms, bridging SSE transports with STDIO proxies.
- Build and extend agent workflows within a bespoke agent SDK.
- Design integrations that trigger on git changes, cloud deployments, or ticketing events for autonomous remediation.
- Package and deploy models as hardened, IP-safe containers.
- Tune high-throughput inference pipelines for structured training data generation.
- Build the observability and telemetry layer for measuring and improving system efficacy.
- Harden the product itself to ensure security.
Requirements
- Natural systems thinker who reasons about data flow, failure modes, and architecture.
- Learns by building and can create working prototypes with new SDKs or protocols.
- Comfortable operating across the stack from model inference to container networking to API design.
- Cares about the entire lifecycle of what they build: observation, testing, scaling, and trust.
- Thinks adversarially by default.
Skills
- TypeScript
- Python
- PostgreSQL
- Docker
- Kubernetes networking
- Hybrid deployment patterns
Location
- Remote
Work Type
- Full-time
Experience Level
- Mid-level
- Senior
About the Company
- We are building a world model for cybersecurity, starting with threat modeling.
- We are building an autonomous threat modeling system that rigorously models attack paths against large-scale infrastructures, orchestrates agents to validate each path, and remediates confirmed vulnerabilities at every step of the attack chain.
- We are hiring a team of engineers to help us scale this from a sharp early product into something that runs autonomously across real-world environments: from git repos to cloud deployments to bug bounty programs.
- Cybersecurity is stuck in a reactive loop: scan, alert, patch, repeat. We're building something that breaks that cycle by reasoning proactively about how systems fail.
