Impress employers and recruiters.
Choose from hundreds of resume examples.
Impress employers and recruiters.
Choose from hundreds of resume examples.
Target Resume Now
About the Role
We are building agents that act within Rakuten's commerce ecosystem, serving as shopping assistants to understand customer needs and find products across a large catalog, as well as merchant-facing agents for listing, pricing, and operations. This role focuses on building the backend systems that ensure agent actions are safe, auditable, and reversible, while maintaining speed for user experience.
Responsibilities
- Build backend services for conversational and autonomous commerce agents, including intent understanding, multi-turn task execution, tool orchestration, and human confirmation checkpoints.
- Own the commerce tool layer, exposing internal commerce APIs for catalog search, product details, inventory and price lookup, cart, checkout, order status, and returns with strict contracts, authorization scoping, and blast-radius limits.
- Solve grounding on a live catalog, managing retrieval over millions of SKUs, attribute and variant normalization, freshness guarantees for price and stock, and preventing agents from recommending non-existent or undeliverable items.
- Design transactional safety for agent actions, implementing idempotency, confirmation and rollback flows, spend and scope limits, permission models, and comprehensive audit trails.
- Build evaluation and observability for commerce outcomes, including task success, recommendation relevance, cart and conversion impact, and containment/escalation rates, with tracing and regression gates.
- Optimize latency and unit economics through retrieval and tool-call budgets, model routing, prompt caching, and cost per resolved task.
- Collaborate directly with commerce product, search/recsys, merchant platform, and trust & safety teams to launch agents into production.
Requirements
- Over 5 years of experience building and operating production backend services.
- Experience developing ML-based production systems (e.g., search, recommendation, ads ranking, personalization, fraud/risk) where model and system quality are intertwined.
- Experience with high-traffic transactional or e-commerce backends (catalog, inventory, cart/checkout, payments, order management), understanding the importance of correctness and consistency.
- Proven track record of shipping quality improvements measured by data, including offline evaluation and online A/B testing.
- Solid distributed systems fundamentals, including async and event-driven architecture, queues, concurrency, idempotency, and distributed tracing.
- Hands-on experience shipping LLM-backed systems to production, including the surrounding infrastructure.
- Direct exposure to agentic patterns such as tool/function calling, orchestration frameworks, and multi-turn state management.
- Experience with cloud and containerized deployment (Kubernetes, CI/CD, IaC).
Skills
- Python
- Go
- Java
- ML-based production systems
- High-traffic transactional backends
- E-commerce backends
- Distributed systems
- Async architecture
- Event-driven architecture
- Queues
- Concurrency
- Idempotency
- Distributed tracing
- LLM-backed systems
- Agentic patterns
- Tool/function calling
- Orchestration frameworks
- Multi-turn state management
- Cloud deployment
- Containerized deployment
- Kubernetes
- CI/CD
- IaC
Location
- Singapore
Work Type
- Full-time
Experience Level
- Over 5 years
About the Company
- Rakuten Group, Inc. is a global leader in internet services with a diverse ecosystem spanning e-commerce, fintech, communications, and more, serving approximately 1.8 billion members worldwide.
- Founded in Tokyo in 1997, the Group operates in over 30 countries and regions with more than 30,000 employees.
- Rakuten Asia Pte. Ltd., based in Singapore's Central Business District, serves as the regional headquarters for Asia, driving value through advertising product development, product strategy, and data management to support Rakuten Group's global ecosystem.