Note: The job is a remote job and is open to candidates in USA. CriticalBridge.AI is an enterprise platform for building, governing, and running AI agents and automated workflows in regulated industries. The Senior Software Engineer will own and extend the Brain, the cloud platform that coordinates and governs AI agents, while working on various components including the control plane and execution runtime.
Responsibilities
- Build and scale the Brain’s control plane: agent registry, work-assignment queue and routing, process orchestration, approval escalation, the event backbone, and the audit log
- Own the agent execution runtime (cloud and local placement) and the ingestion pipeline that parses documents, extracts entities, and builds the knowledge graph
- Strengthen our multi-tenant isolation model across messaging, identity, secrets, and the data layer — isolation is a feature our customers pay for
- Build the compliance and governance infrastructure: validation gates, human-in-the-loop enforcement, and tamper-evident audit built to satisfy regulated buyers
- Work across the data layer — Cloud SQL (Postgres) coordination ledgers, GCS artifacts, Redis caching, pgVector RAG, and the Neo4j knowledge graph — and the LLM provider-abstraction layer
- Own reliability, observability, and cost: distributed tracing, alerting, Cloud Run concurrency tuning, and the per-entity scaling levers
- Ship infrastructure as code (Terraform) and CI/CD through Cloud Build / Cloud Deploy / Artifact Registry
Skills
- 5+ years building production backend systems, with strong TypeScript/Node.js (we'll consider strong engineers from other typed backgrounds who are eager to go deep in TS)
- Solid distributed-systems fundamentals: queues, event-driven systems, idempotency, concurrency, data consistency, and failure handling
- Hands-on cloud-native experience — Google Cloud strongly preferred (Cloud Run, Pub/Sub, Cloud SQL, IAM, Secret Manager), but strong AWS/Azure backgrounds welcome
- Comfort with Postgres at depth, plus IaC (Terraform) and CI/CD pipelines
- A bias toward correctness, observability, and clean, well-tested code — you sweat the edge cases because our customers are regulated
- Multi-tenant SaaS isolation, enterprise security, or compliance (SOC 2, regulated verticals)
- AI/LLM systems: agent orchestration, RAG, embeddings/vector search, eval pipelines
- Knowledge graphs (Neo4j), pgVector, or document-ingestion DAGs
- Insurance, finance, or healthcare domain exposure
Benefits
- Comprehensive health, dental, and vision insurance
- Paid Time Off (PTO) and company holidays
Company Overview