Agentic Infrastructure Engineer Intern

XPENG is a leading smart technology company at the forefront of innovation, integrating advanced AI and autonomous driving technologies into its vehicles, including electric vehicles (EVs), electric vertical take-off and landing (eVTOL) aircraft, and robotics. With a strong focus on intelligent mobility, XPENG is dedicated to reshaping the future of transportation through cutting-edge R D in AI, machine learning, and smart connectivity. XPENG is building the next generation of enterprise AI infrastructure — autonomous, application-driven systems that power real-time decision making across autonomous driving and AI platforms.

As part of our AI Enablement team, you will work on internal platforms at the frontier of LLM orchestration, multi-agent coordination, and automated workflow systems. This role is ideal for candidates passionate about developer productivity, AI-native tooling, and scalable infrastructure. You will build systems for CI/CD, observability, evaluation, and workflow automation, while working closely with senior engineers across AI infrastructure and platform teams.

Key Responsibilities

Design and implement Electron-based desktop applications for prompt workflow visualization, process inspection, and self-service dashboards for non-engineering stakeholders. Contribute to JavaScript/TypeScript components that enable LLM orchestration, AI workflow interoperability, pipeline automation, and MCP-compatible connectors. Build and extend evaluation frameworks for verifying agent outputs and system reliability, including LLM-as-judge metrics, structured validation, and automated feedback loops.

, LangFuse, OpenTelemetry, custom metrics) and develop automated dashboards to surface runtime insights and model performance trends. Participate in the full engineering lifecycle including design reviews, implementation, testing, CI/CD integration, and Git-based collaboration workflows. Collaborate closely with platform engineers and researchers on benchmark selection, failure analysis, prompt optimization, and quantitative evaluation methodologies.

Qualifications

D. program in Computer Science, Software Engineering, Electrical Engineering, or a related technical field. Strong proficiency in JavaScript/TypeScript and modern frontend/backend development practices.

Experience with Electron Framework, including desktop application development, IPC communication, and renderer/main process architecture. Familiarity with AI agent systems, LLM tooling frameworks, orchestration pipelines, or evaluation workflows. Understanding of CI/CD fundamentals, automated testing pipelines, artifact publishing, and developer productivity tooling.

Experience designing evaluation or verification systems for AI outputs, structured data validation, or workflow automation. Strong communication and documentation skills with the ability to clearly present technical ideas, PRs, reports, and experimental findings.

Preferred Qualifications

: Experience building internal AI developer tools, observability platforms, or workflow orchestration systems. Familiarity with modern AI infrastructure frameworks such as LangFuse, OpenTelemetry, MCP, or related tooling ecosystems. Experience with prompt engineering, automated evaluation pipelines, or agent reliability optimization.

Knowledge of modern frontend application architecture and performance optimization for Electron-based systems. Experience working in fast-paced engineering environments with rapid iteration cycles and cross-functional collaboration. Contributions to open-source projects or prior experience developing scalable AI infrastructure platforms.

What We Are Looking For

: Self-motivated and proactive in solving problems. Comfortable operating in fast-moving, ambiguous environments. Strong in debugging, systems thinking, and iterative problem solving.