Senior Backend Engineer, Shopping Agents at Sage AI Labs in San Francisco

Job description

• Application
• Senior Backend Engineer, Shopping Agents
• Sage AI Labs · San Francisco · Full-time · [Onsite]
• We build agents that shop for you. They find products across the open web and complete the purchase end to end. Real carts, real payments, and real systems built to stop them.
• You would own that. Architecture, code, deploys, monitoring, and on-call for systems that transact around the clock, working directly with our CTO.
• Why this role
• Very few engineers get to own a category-defining system while the category is still being defined. This is one of those seats, at the point where it still counts as early. A year from now this problem will have a standard answer and someone will have written it. We intend for that to be us.

Responsibilities

• Our checkout agents. Frontier-model computer-use agents driving live checkouts at scale, plus the machinery that keeps them standing when the ground moves. Every retailer breaks differently and they change without warning. Your job is to make failure rare and recovery automatic.
• Ingestion at scale. Take product ingestion from hundreds of sources to thousands. The answer is not more hand-written code. It is infrastructure that generates, validates, and monitors itself.
• Search and ranking. Embedding-based retrieval, LLM query understanding, reranking, and caching, across a catalog that never stops changing.

Requirements

• 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 have been the person who got paged, and you fixed the class of problem rather than the incident
• 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, not a red build
• You can move without a finished spec. We are small, and the roadmap changes when the market does
• Built AI-first products or LLM-based agents in production, not just in a prototype
• Working knowledge of classic ML and deep learning, enough to reason about retrieval and ranking rather than only calling an API
• Background in e-commerce, payments, or fraud and risk infrastructure

Skills

Required

• Strong Python
• Backend and infrastructure systems
• Adversarial problem solving
• Correctness and reliability
• Ability to work without finished specs

Preferred

• Classic ML and deep learning

Benefits

• Meaningful early-stage equity
• Medical, dental, and vision coverage; other benefits
• San Francisco based