AI Systems / Agent Engineer (Remote)

About the role

We are looking for an AI Systems / Agent Engineer to design and build a robust engineering harness that enables a specialist AI model to function as an end‑to‑end software engineer. This remote position focuses on integrating the model with development tools, ensuring reliable execution of software‑engineering tasks.

Key responsibilities

• Design and implement the agent architecture around specialist models.
• Develop repository understanding, codebase retrieval, and integration with Git, compilers, debuggers, test runners, and development environments.
• Create planning‑execution‑testing‑evaluation‑correction loops and automated performance/load‑testing workflows.
• Integrate architecture/dependency analysis, security, and static‑analysis tooling.
• Build model verification, critic/evaluator systems, and tool‑use/function‑calling infrastructure.
• Implement safeguards that prevent models from modifying code without proper context.
• Develop observability and evaluation infrastructure for agent behavior.
• Collaborate with Model Research Engineers to feed real‑world failures back into model training.

Required profile

• Strong experience in AI agent or ML systems engineering.
• Background building production‑grade coding agents or developer tools.
• Proficiency in Python and TypeScript with solid backend engineering skills.
• Experience with tool calling, orchestration, and agent frameworks.
• Deep understanding of software architecture, RAG, code retrieval, and knowledge graphs.
• Familiarity with Docker, Kubernetes, CI/CD pipelines, and cloud infrastructure.
• Experience building evaluation and observability systems for AI agents.

Required skills

• Python
• TypeScript
• Git
• Compilers
• Debuggers
• Test runners
• Docker
• Kubernetes
• CI/CD pipelines
• Cloud infrastructure
• RAG (Retrieval‑Augmented Generation)
• Knowledge graphs
• Static analysis
• Code security
• Performance engineering
• SWE‑bench
• LangGraph
• Claude Agent SDK
• OpenAI Agents SDK