Full-Stack Software Engineer, Core Platform

About Lumbra

Lumbra builds the vendor-neutral operating system for agentic AI in high-consequence environments. In our first ten months we won four U.S. Government prime contracts in open competition, every one deploying into classified spaces, and we are live on JWICS. We were selected from a field of more than 200 companies and won, beat two established defense primes head to head, and earned the follow-on now in execution. Lumbra is a team of engineers and operators from the intelligence community, special operations, and frontier AI research, with degrees from MIT, Carnegie Mellon, and West Point, and careers built at Palantir, Anduril, Northrop Grumman, Onebrief, JSOC, NSA, and CIA. They have lived this problem from the inside.

About the Role

Nebula turns days of manual synthesis into minutes of analysis. We want a full-stack engineer to own features end to end across the Python backend and the React frontend, putting real AI tooling directly in analysts' hands.

What You'll Own

• Design and build FastAPI endpoints backed by PostgreSQL and SQLAlchemy for agent configuration, workflow orchestration, and evaluation pipelines.

• Implement interactive React and TypeScript features: conversation interfaces, workflow visualization, and knowledge-graph exploration.

• Build durable workflow orchestration for long-running agent execution, including delegation, monitoring, and timeout propagation.

• Own features across the full stack, from database migration through API contract to UI state.

• Bring clean abstractions and well-defined interfaces to a fast-moving codebase, writing code that survives constant change and stays easy to understand, refactor, and extend.

• Write contract-driven tests across backend and frontend that cover the spec rather than the implementation, working test-first.

• Design testing for non-deterministic AI components: metamorphic testing, property-based testing, and regression suites that catch capability loss without overfitting to specific outputs.

• Contribute to the Python and TypeScript client SDKs so programmatic consumers get ergonomic, well-typed access.

• Own performance across the stack and profile before guessing: API latency, query efficiency, render performance, and end-to-end streaming latency. Treat slowness as a defect.

• Debug across service boundaries with local environments and distributed tracing.

Required Qualifications

• Ships production Python (async, relational modeling, layered services) and production React and TypeScript

• Reasons comfortably about data flow through every layer, from schema to UI state

• Writes clean, well-tested code and works test-first

Preferred Qualifications

• Agentic AI systems: harness engineering, context engineering, or building on LLM APIs

• Distributed task orchestration systems

• Graph databases or vector search for knowledge representation and retrieval

• Model Context Protocol or similar tool-use frameworks

• Identity management (OAuth2/OIDC)

• Open-source developer-tooling contributions

• Intelligence analysis, OSINT, or analytical workflows that inform product intuition

• Cloud infrastructure (GCP or equivalent): managed Kubernetes, managed databases, secrets management
  
  Benefits

• Comprehensive medical, dental, and vision plans

• Premiums 100% covered by Lumbra for all employees

• Exceptionally low premiums for spouses and dependents

• Basic life insurance and disability 100% covered for all employees by Lumbra

• Option to purchase additional life insurance available

• Take the time off that you need, when you need it' paid time off, not accrual based

• Generous company holiday calendar including a holiday shutdown in December

• Supportive leave of absence program including time off for military service, medical events, and parental leave

• Full 401(k) retirement plan for all full-time eligible employees

• Company-funded commuter benefits

• Free access to on-site gym at office