Forward Deployment Engineer (AI)

Location: Tokyo Prefecture, Japan; willingness to travel up to 50% to customer sites is required.

Salary: ¥10,500,000–¥13,000,000 JPY per year

Company

hirify.global develops full-stack AI inference infrastructure based on RDU hardware, SambaRack systems, and the SambaStack enterprise inference serving platform.

What you will do

• Embed with strategic enterprise customers to design, build, and deploy production generative AI applications on the SN40L platform and SambaStack.
• Architect LLM-powered workflows, including RAG pipelines, multi-agent systems, fine-tuning workflows, and coding solutions.
• Optimize inference performance by benchmarking throughput, latency, and accuracy against customer requirements and competitor baselines.
• Troubleshoot production issues across model, software, and hardware layers as the primary technical escalation point.
• Translate customer needs into product requirements and engineering feedback while partnering with sales and solutions engineering teams.
• Develop reusable accelerators, reference architectures, and playbooks, and present technical findings to customers and internal teams.

Requirements

• 5+ years of hands-on engineering experience shipping production AI/ML systems.
• Deep expertise in LLM orchestration, RAG, agentic frameworks, prompt engineering, and evaluation pipelines.
• Strong knowledge of model training, fine-tuning, inference optimization, quantization, and performance benchmarking.
• Proficiency in Python; working knowledge of C++ or CUDA is beneficial for hardware-layer debugging.
• Experience with AWS, Azure, or GCP, plus containerization, Kubernetes, Docker, and MLOps tooling.
• Bachelor's or graduate degree in Computer Science, Electrical Engineering, Mathematics, Physics, or equivalent practical experience.

Nice to have

• Experience with AI accelerators or custom silicon, including TPUs.
• CUDA or low-level GPU programming experience.
• Familiarity with vLLM or SGLang.
• Enterprise AI deployment experience in regulated industries.

Culture & Benefits

• Work on an integrated hardware and software platform for generative AI inference and high-performance computing.
• Collaborate with enterprise customers, Product and Engineering teams, Account Executives, and Solutions Engineers.
• Represent the platform at customer briefings, industry conferences, and technical events.
• Benefits described in the posting apply to US-based full-time employment positions and include medical, dental, vision, disability, life, HSA, FSA, wellness, and counseling programs.