Senior Backend Engineer, Shopping Agents

Sage AI Labs

Warsaw, Poland

Remote

Who this role is best for

Best suited to backend engineers with strong Python and e-commerce experience, working in a collaborative, fast-moving environment where ownership of production systems is critical.

Best fit for

Candidates with 5+ years of end-to-end production system ownership and a track record in adversarial system design
— “You have owned production systems end to end: deploys, databases, observability, and the pager.”
Individuals who have experience building AI-first products and LLM-based agents in production
— “Built AI-first products or LLM-based agents in production, not just in a prototype”
Engineers with a background in e-commerce, payments, or fraud and risk infrastructure
— “Background in e-commerce, payments, or fraud and risk infrastructure”

Things to consider

The role demands handling high-stakes systems where silent failures can lead to financial consequences for users
— “the stakes are real. These systems spend customers' money, so a silent failure is a wrong order, not a red build”
Candidates must be comfortable with evolving requirements and adapting to market changes
— “the roadmap changes when the market does”

How to stand out

Highlight experience with self-generating infrastructure and real-time monitoring of live systems
— “infrastructure that generates, validates, and monitors itself”
Emphasize your ability to fix systemic issues, not just individual incidents, in your on-call or production ownership history
— “You have been the person who got paged, and you fixed the class of problem rather than the incident”
Showcase your work with embedding-based retrieval, reranking, and caching systems for dynamic data
— “Embedding-based retrieval, LLM query understanding, reranking, and caching, across a catalog that never stops changing.”

Pace · Fast PacedCollaboration · MediumAutonomy · HighDecision Impact · Company

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

own production systems end to end
build checkout agents
handle ingestion at scale
embed search and ranking

Typical background

5+ years of backend and infrastructure systems building

Skills & requirements

Required

Python Backend DevelopmentProduction Systems OwnershipInfrastructure Systems BuildingAdversarial Problem SolvingCorrectness PrioritizationAbility To Work Without A Finished Spec

Preferred

Ai-first ProductsLlm-based AgentsE-commercePaymentsFraud And Risk Infrastructure

Stack & domain

PythonBackend DevelopmentInfrastructure SystemsProduction SystemsDatabasesObservabilityAdversarial ProblemsCorrectnessAi-first ProductsLlm-based AgentsClassic MLDeep LearningE-commercePaymentsFraud And Risk InfrastructureCollaborationProblem-solvingCuriosityProactivityContinuous LearningCommerceTechnology

About the role

Original posting from Sage AI Labs via Ashby

SENIOR BACKEND ENGINEER, SHOPPING AGENTS
Sage AI Labs · Warsaw · Full-time · [Onsite & Remote]
ABOUT US
Sage AI Labs is building the infrastructure that lets AI agents transact on the open web. It is one of the few genuinely unsolved problems left in commerce, and whoever solves it sets the defaults everyone else builds on top of.
The company was founded by Sebastian Thrun (founder of Google X and Waymo, Udacity) and is backed by leading venture and strategic investors.
ABOUT THE ROLE
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.
WHAT YOU'LL OWN
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.
WHAT WE'RE LOOKING FOR
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
NICE TO HAVE
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
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.

Source: Sage AI Labs careers (Ashby)