Skip to content
Search jobs inside your AI agent. Claude, ChatGPT, Claude Code, Codex, Gemini, Cursor and Grok
Connect

Specialized Group

NewBe an early applicant

AI Harness Engineer – AI Agents & LLM Infrastructure

Posted Updated

Summary

Builds the infrastructure and engineering systems behind AI agents and enterprise LLM applications: agent execution environments, tool integrations, memory/context management, and evaluation/monitoring frameworks. Focused on making LLMs production-ready using Python/TypeScript, distributed systems, and cloud infrastructure.

AI Harness Engineer – AI Agents & LLM InfrastructureAbout the OpportunityAn innovative, fast-growing AI company is hiring an AI Harness Engineer to build the infrastructure and engineering systems that power next-generation AI agents and enterprise AI applications.

This position sits at the intersection of software engineering, LLM infrastructure, and agentic AI development. You'll focus on building the tools, execution environments, and orchestration frameworks that enable AI agents to perform complex tasks reliably, efficiently, and at scale.

Unlike traditional AI engineering roles focused primarily on model development, this opportunity emphasizes building the systems around AI models, transforming powerful LLMs into reliable, production-ready autonomous applications.

Key Responsibilities

  • Design and develop AI agent harnesses, including execution environments, tool integrations, and orchestration frameworks.
  • Build infrastructure enabling LLM-powered agents to interact with external tools, APIs, databases, and enterprise systems.
  • Develop robust systems for agent memory, context management, task execution, and workflow automation.
  • Implement evaluation, monitoring, and debugging frameworks to improve agent reliability, performance, and safety.
  • Optimize LLM-powered workflows for latency, scalability, cost efficiency, and production stability.
  • Collaborate with AI researchers, software engineers, and product teams to bring advanced agentic AI capabilities into real-world applications.

What We're Looking For

  • 3+ years of professional software engineering experience, ideally in backend, platform, or infrastructure development.
  • Strong programming skills in Python, TypeScript, or similar languages.
  • Practical experience working with LLMs, Generative AI, or AI agent frameworks.
  • Solid understanding of APIs, distributed systems, cloud infrastructure, and modern software architecture.
  • Familiarity with agent orchestration, tool calling, RAG, or context management techniques.
  • Experience designing, deploying, and maintaining reliable production software systems.
  • Business Japanese level
  • Strong problem-solving skills and an interest in pushing the boundaries of autonomous AI systems.

Why Consider This Opportunity?

  • Work at the forefront of Agentic AI, autonomous systems, and LLM infrastructure.
  • Build the foundational engineering systems that make AI agents more capable, reliable, and production-ready.
  • Gain hands-on exposure to cutting-edge technologies, including multi-agent orchestration, tool-use systems, and advanced AI workflows.
  • Take ownership of technically challenging projects with significant influence over architecture and engineering decisions.
  • Collaborate closely with talented AI engineers and researchers in a fast-moving technical environment.
  • Help shape the next generation of enterprise AI applications as the industry moves beyond basic chatbots toward autonomous AI agents.

If you're a software engineer who enjoys building complex systems, solving challenging infrastructure problems, and enabling AI agents to operate reliably in the real world, this could be an exciting next step in your career.

Skills

Apply

See also

AI Engineering jobs by country — openings, pay and top skills →