Backend Engineer, Agent Development (EC AI)

About the role

Rakuten Asia Pte. Ltd., based in Singapore's Central Business District, is hiring a Backend Engineer for its AI & Data Division (AIDD), which builds AI-powered search, recommendation, advertising and optimization solutions. The team is building agents that act inside Rakuten's commerce ecosystem: shopping assistants that find items across a large multi-merchant catalog, and merchant-facing agents that handle listing, pricing and operations. These agents take real actions on real commerce state (adding to carts, applying coupons, initiating returns, updating listings, triggering fulfillment), so the backend must make those actions safe, auditable and reversible.

Key responsibilities

• Build the backend services behind conversational and autonomous commerce agents: intent understanding, multi-turn task execution, tool orchestration and human confirmation checkpoints.
• Own the commerce tool layer (catalog search, product details, inventory and price lookup, cart, checkout, order status, returns), exposing internal APIs to agents with strict contracts, authentication 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 recommendations for items that do not exist or cannot ship.
• Design transactional safety: idempotency, confirmation and rollback flows, spend and scope limits, permission models and audit trails for every agent action.
• 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.
• Optimize latency and unit economics: retrieval and tool-call budgets, model routing, prompt caching, and cost per resolved task.
• Work with commerce product, search/recsys, merchant platform and trust & safety teams to ship agents through launch review into production.

Required profile

• 5+ years building and operating production backend services; strong in Python (Go or Java a plus).
• Experience developing ML-based production systems such as search, recommendation, ads ranking, personalization or fraud/risk, owning both model and system quality.
• Experience with high-traffic transactional or e-commerce backends: catalog, inventory, cart/checkout, payments or order management.
• Track record of shipping quality improvements measured by data, including offline evaluation and online A/B testing.
• Direct exposure to agentic patterns: tool/function calling, orchestration frameworks and multi-turn state management.

Required skills

• Solid distributed systems fundamentals: async and event-driven architecture, queues, concurrency, idempotency, distributed tracing.
• Hands-on experience shipping LLM-backed systems to production.
• Cloud and containerized deployment experience (Kubernetes, CI/CD, IaC).