Senior Staff Platform Engineer - End-to-End Agent Stack

Precision Labs; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Sapiom is seeking a Senior Staff Engineer to own one system end-to-end, from routing and capacity to metering and reliability. You will optimize model calls for latency, cost, and quality while maintaining strong governance across the platform.

As you shape the control plane with credential-scoped permissions and spend controls, you’ll ensure billing correctness and robust observability. This role emphasizes handling high-scale events and building for reliability in production.

Qualifications

• Own a production system end-to-end and carry the pager.
• Billing, payments, ledgers, or anything that must reconcile against another number.
• Design for failure up front—timeouts, retries, idempotency; explain what changed after a failure.
• Debug production issues under time pressure and document findings.

Responsibilities

• Routing and capacity: place model calls against latency, cost, and quality targets in real time.
• Metering and billing correctness: ensure two charging layers reconcile across 270M+ events.
• Reliability at sustained scale: improve observability, incident practice, and architecture as growth continues.
• The control plane: credential-scoped permissions and governance for safe agent control.
• Spend controls: budgets enforced before money moves and clear downstream reporting.

Skills

Production systems ownership

Billing/ledger experience

Reliability at scale

Observability

AI tooling in engineering workflow

Tools

Cloud infrastructure

API gateways

Billing systems

Monitoring/Observability tools

Job description

Sapiom is seeking a Senior Staff Engineer to own one system end-to-end, from routing and capacity to metering and reliability. You will optimize model calls for latency, cost, and quality while maintaining strong governance across the platform.

As you shape the control plane with credential-scoped permissions and spend controls, you’ll ensure billing correctness and robust observability. This role emphasizes handling high-scale events and building for reliability in production.