Senior Backend Engineer - AI-Driven Checkout Infrastructure

Stealth Startup; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Meaningful equity

Medical, dental, and vision

On-site San Francisco

Job summary

Sage AI Labs in San Francisco is seeking an experienced backend engineer to own production systems and infra that power AI agents transacting on the open web. You will design, deploy, monitor, and on-call for systems that operate 24/7, collaborating with the CTO and platform team.

You'll own the ingestion and processing pipelines, scale ingestion from hundreds of sources to thousands, and build resilient, self-monitoring infrastructure with reliable search and ranking across a dynamic catalog.

Qualifications

• 5+ years building backend and infrastructure systems, with strong Python.
• You have owned production systems end to end: deploys, databases, observability, and the pager.
• You like adversarial problems. Systems where something on the other side is actively working against you.
• You take correctness seriously because the stakes are real. These systems spend customers' money, so a silent failure is a wrong order.
• You can move without a finished spec. We are small, and the roadmap changes when the market does

Responsibilities

• Own our checkout agents, including architecture and deployment for live transactions.
• Scale ingestion from hundreds of sources to thousands of items; build infrastructure that generates, validates, and monitors itself.
• Develop embedding-based retrieval and ranking components across a changing catalog

Skills

Backend systems

Python

Observability

Production ownership

Adversarial problems

Reliability

Job description

Sage AI Labs in San Francisco is seeking an experienced backend engineer to own production systems and infra that power AI agents transacting on the open web. You will design, deploy, monitor, and on-call for systems that operate 24/7, collaborating with the CTO and platform team.

You'll own the ingestion and processing pipelines, scale ingestion from hundreds of sources to thousands, and build resilient, self-monitoring infrastructure with reliable search and ranking across a dynamic catalog.