LLM Application Engineer (AI)

Location: Hybrid in Seoul, South Korea

Company

hirify.global's ActAI Engineering team builds proactive AI-native applications for conversations, errands, organization, and workflows, with a focus on reliable long-running execution and real-world task completion.

What you will do

• Build and ship LLM-powered applications and AI agent workflows.
• Design systems for reasoning, planning, memory, tool use, and multi-step execution.
• Develop reliable orchestration pipelines that turn model outputs into predictable, observable, and safe actions.
• Integrate LLMs with APIs, databases, search systems, internal services, and external tools.
• Build evaluation frameworks and datasets to measure AI quality, reliability, and regressions.
• Optimize AI systems for quality, latency, cost, observability, and continuous improvement.

Requirements

• Strong software engineering fundamentals and experience building AI-powered applications.
• Hands-on experience with LLMs, generative AI, or agent-based systems.
• Experience designing prompts, workflows, evaluations, or AI behavior.
• Ability to write clean, production-quality Python code.
• Comfort working across model, system, and product abstraction layers in ambiguous, fast-moving environments.
• Experience or familiarity with LLM APIs, agent frameworks, vector databases, retrieval systems, backend services, distributed systems, PyTorch, or JAX.

Culture & Benefits

• End-to-end ownership of AI problems, from user needs through production deployment.
• Close collaboration with product and engineering teams to turn ambiguous problems into working AI solutions.
• Fast iteration focused on measurable user impact and continuous improvement.
• Production practices include observability, tracing, experimentation, evaluation, and regression monitoring.