Forward Deployed Engineer (AI)

TL;DR

Forward Deployed Engineer (AI): Serving as the primary technical contact for customers to drive the adoption of AI solutions with an accent on designing production-ready AI inference infrastructure. Focus on optimizing workload performance, troubleshooting deployment bottlenecks in Kubernetes environments, and bridging the gap between customer needs and internal hardware/software development teams.

Location: Seongnam, South Korea (Onsite at R-TOWER).

Company

hirify.global is an AI semiconductor company specializing in high-performance inference solutions.

What you will do

• Act as the primary technical contact for customers throughout the engagement lifecycle.
• Design and deploy production-ready AI inference infrastructure with high availability.
• Evaluate end-to-end performance and identify system-level bottlenecks.
• Optimize workload scheduling and routing strategies for AI inference.
• Create technical documentation, integration guides, and best practices.
• Collaborate with internal engineering teams to influence product direction based on customer feedback.

Requirements

• Bachelor's degree in Computer Science, Electrical Engineering, or a related field.
• Hands-on experience with Python and Kubernetes-based environments.
• Deep understanding of AI inference and serving frameworks like vLLM or TensorRT-LLM.
• Working knowledge of PyTorch.
• Strong communication and collaboration skills for customer-facing engagements.

Nice to have

• Experience designing and benchmarking end-to-end AI inference systems.
• Knowledge of hardware acceleration (NPU, GPU, edge chips) and model optimization techniques (quantization, pipelining).
• Prior experience in technical customer-facing roles like Solutions or Sales Engineering.

Hiring process

• Document review, online interview, on-site interview, and culture-fit assessment.