Backend Engineer, Agent Development - AI Lab (AILAB)

掲載中・1日前に確認

給与: 記載なし
勤務地: 東京都
休日: 記載なし
雇用形態: 記載なし

どんな仕事かAIによる生成

楽天のコマース領域で、会話型・自律型エージェントを支えるバックエンドを構築するポジションです。カタログ検索やカート、注文、返品などの機能をエージェントに提供し、実際の取引操作の安全性、監査可能性、可逆性を担保します。評価・可観測性の構築やレイテンシーとコストの最適化にも取り組みます。

応募資格・募集要項・仕事内容を見る

この求人に応募

給与記載なし

募集元で応募する楽天グループ株式会社の採用ページへ

相談する共有準備中

応募は募集元の採用ページで受け付けています。当サイトに応募フォームはありません。

応募資格

必須

Over 5 years building and operating production backend services; strong in Python (Go or Java a plus)
Experience developing ML-based production systems - search, recommendation, ads ranking, personalization, or fraud/risk. You've owned a system where model quality and system quality were the same problem
Experience with high-traffic transactional or e-commerce backends: catalog, inventory, cart/checkout, payments, or order management - you understand why correctness and consistency matter more here than in most systems
Track record of shipping quality improvements measured by data: offline evaluation, online A/B testing, and the judgment to know when they disagree and why
Solid distributed systems fundamentals: async and event-driven architecture, queues, concurrency, idempotency, distributed tracing
Hands-on experience shipping LLM-backed systems to production - not just API calls, but the infrastructure around them
Direct exposure to agentic patterns: tool/function calling, orchestration frameworks, multi-turn state management
Cloud and containerized deployment experience (Kubernetes, CI/CD, IaC)

募集要項最終確認 10/15

職種: バックエンドエンジニア
雇用形態: 記載なし
給与: 記載なし
勤務地: 東京都, 東京都
働き方: 記載なし
経験年数: 5年以上
掲載日: 2026/09/02 18:18（44日前）
最終確認: 2026/10/15 21:35（1日前）

仕事内容

Department Overview

The AI & Data Division (AIDD) creates powerful, customer-focused search, recommendation, data science, advertising, marketing, price, and inventory optimization solutions for businesses across the Rakuten group.
As part of AIDD, AI Lab builds new solutions that have the potential to transform how users interact with Rakuten services. Our goal is to drive innovation by developing new products and capabilities that deliver significant impact over longer timeframes using AI.

Position Details

We're building agents that work inside Rakuten's commerce ecosystem - shopping assistants that understand what a customer actually wants and find it across a vast, messy, multi-merchant catalog; and merchant-facing agents that handle listing, pricing, and operations work that used to require a human in a dashboard. The distinguishing constraint of this role: these agents take real actions on real commerce state. They add to carts, apply coupons, initiate returns, update listings, trigger fulfillment. A hallucinated sentence is an inconvenience; a hallucinated order is an incident. You'll build the backend that makes agent actions safe, auditable, and reversible - while keeping them fast enough for a shopper who won't wait four seconds.
Build the backend services behind conversational and autonomous commerce agents: intent understanding, multi-turn task execution, tool orchestration, human confirmation checkpoints
Own the commerce tool layer - catalog search, product detail, inventory and price lookup, cart, checkout, order status, returns - exposing internal commerce APIs to agents with strict contracts, auth scoping, and blast-radius limits
Solve grounding on a live catalog: retrieval over tens of millions of SKUs, attribute and variant normalization, freshness guarantees on price and stock, and preventing agents from confidently recommending things that don't exist or can't ship
Design transactional safety for agent actions: idempotency, confirmation and rollback flows, spend and scope limits, permission models, and full audit trails for every action an agent takes on a user's or merchant's behalf
Build evaluation and observability for commerce outcomes - task success, recommendation relevance, cart and conversion impact, containment and escalation rates - with tracing across multi-step runs and regression gates before release
Optimize latency and unit economics: retrieval and tool-call budgets, model routing, prompt caching, cost per resolved task measured against the revenue or support cost it moves
Work directly with commerce product, search/recsys, merchant platform, and trust & safety teams to ship agents through launch review into production

この求人は、楽天グループ株式会社の採用ページの内容をAIが読み取って整理したものです。応募の前に採用ページの原文を確かめてください。データの集め方企業サイト