Senior/Staff Founding Full-Stack Engineer

This is a founding engineering role that is deliberately backend- and systems-heavy - “full-stack” here means owning the product and the system end-to-end. You’ll be building the core machinery that lets autonomous agents act safely inside real production environments: how work is orchestrated, how identity and permissions are governed, and how sensitive credentials are handled.

What you’ll be doing

• Build the workflow engine for long-running human and agent work: durable state, retries, idempotency, approvals, replay, compensation, and auditability
• Design identity and authorization for humans, services, and agents: principals, delegation, scoped sessions, tenant isolation, and traceable authority
• Build a versioned policy engine governing who or what can perform which action, on which resource, under what context
• Own secure storage and use of customer keys, OAuth tokens, and admin credentials: isolation, rotation, ephemeral injection, revocation, and blast-radius containment
• Own the boundary between probabilistic model behavior and deterministic execution: validation, evals, and release gates
• Build isolated virtual environments and dev boxes for agents, and ship the interfaces and APIs to author, approve, inspect, debug, and operate all of this in production, * Genuine founding-engineer scope with true end-to-end ownership of product and system
• A well-backed seed-stage team already live with design partners
• Deep, meaningful systems and security problems at the frontier of agent infrastructure

• Senior/Staff-level engineer, strongest in backend and systems architecture, and comfortable reaching across frontend, data, infrastructure, and product
• A track record of designing and operating complex production systems, and the ability to talk through what broke, how you recovered, and what you changed
• Real depth in at least one of: IAM/authorization, policy systems, workflow orchestration, security, multi-tenant SaaS, agent infrastructure, or virtualized execution
• A rigorous engineering mindset - reasons in invariants, threat models, failure modes, and user outcomes
• Moves quickly from ambiguity without trading away correctness, security, or operability
• Able to work on-site in San Francisco, Monday to Friday, at startup intensity, * A standout signal of excellence in some area - leading an important team at a high-growth company, top competitive-programming results, or elite achievement in another demanding pursuit
• A CS/engineering degree from a top program, or genuinely exceptional experience in its place
• Time spent on a high-caliber team at a strong engineering company
• A big-tech background, for the scalability and security depth it brings
• A high-agency track record - former founders, or early engineers who owned architecture, production, and customer-facing product

Our client is a seed-stage startup building AI coworkers for IT and security teams - an agent that registers as a governed identity, requests scoped access one task at a time, and acts only under human approval. They’ve raised a $6M seed from a strong group of operators and investors, and are already working with several design partners as a small founding team.

Founded 2026 · 1-10 people · Industry: AI tooling for IT & security