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

The AI & Data Division (AIDD) creates powerful, customer-focused solutions using AI. The LLMAD team drives adoption of Rakuten AI and open-source LLMs by embedding AI Engineers within business units to drive adoption of in-house large language models.

Responsibilities

• Own a business unit engagement end to end, embedding in their engineering team.
• Design the agent, including task decomposition, tool and function calling, multi-step orchestration, state, retrieval, and guardrails.
• Write production code within the business unit's codebase.
• Take agents from prototype to production, managing latency, cost, failure modes, and monitoring.
• Determine if an agent is the wrong answer and suggest alternatives like prompts, fine-tuning, or plain software.
• Select appropriate in-house or open-source models for tasks and prove their effectiveness with task-level evaluation.
• Build evaluation sets and harnesses in collaboration with the business unit.
• Migrate applications from third-party APIs to in-house models, including parity testing, prompt porting, and staged cutover.
• Provide feedback on model and platform gaps to relevant teams.
• Own prompt and context engineering, including structured output, tool schemas, retrieval strategy, and caching.
• Debug quality issues by identifying whether the fault lies with the prompt, retrieval, model, or data.
• Create reusable cookbooks, recipes, and reference implementations for other business units.
• Improve team standards through code review, mentorship, and hands-on enablement for business unit engineers.
• Write agent and integration code within the business unit's product.
• Be accountable for shipping code on Rakuten's models.

Requirements

• Over 6 years of professional software engineering experience with a recent hands-on focus on building LLM applications.
• Proven agentic engineering experience, including building, shipping, evaluating, and debugging agents in production.
• Experience with tool and function calling, multi-step orchestration, and associated failure modes.
• Proficiency in prompt and context engineering, including structured outputs, systematic iteration against evaluations, and versioning.
• Practical knowledge of model strengths and weaknesses (open-weight and commercial), fine-tuning vs. prompting vs. retrieval, and cost/latency trade-offs.
• Solid production fundamentals, including APIs, backend services, testing, observability, and experience with self-hosted or cloud inference (e.g., vLLM).
• Ability to work embedded in another engineering team.
• Ability to communicate directly with business stakeholders.
• Ability to operate with ambiguity in a developing function.
• Skill in documenting work through docs, examples, and recipes for other engineers.

Skills

• LLM applications
• Agentic engineering
• Tool and function calling
• Multi-step orchestration
• Prompt engineering
• Context engineering
• Model evaluation
• Production software engineering
• API development
• Backend services
• Testing
• Observability
• Self-hosted inference
• Cloud inference
• vLLM
• Retrieval-augmented generation
• Fine-tuning
• Post-training

Location

• Japan

Work Type

• Embedded
• Full-time

Experience Level

• Senior
• Over 6 years of professional software engineering experience

About the Company

• Rakuten Group, Inc. is a global leader in internet services, empowering individuals, communities, businesses, and society.
• Founded in Tokyo in 1997, Rakuten offers services in e-commerce, fintech, digital content, and communications.
• Serves approximately 1.7 billion members worldwide.
• Has nearly 32,000 employees and operations in 30 countries and regions.