Senior AI Engineer

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.

We are looking for a hands‑on Senior Staff AI Engineer to build and scale production‑grade AI systems that drive measurable impact across internal teams. This role owns the end‑to‑end delivery of applied AI solutions—partnering with product, engineering, and cross‑functional teams across the organization to identify high‑value use cases, and translating them into scalable systems using LLMs, retrieval, and agentic workflows. You will also define architecture and reusable patterns to enable AI adoption broadly, while setting a high bar for reliability, evaluation, and performance.

• Lead the technical design and hands‑on development of prioritized AI applications, services, and platforms leveraging state‑of‑the‑art LLM app stacks, retrieval‑augmented generation, evaluation frameworks, and scalable serving.
• Define long‑term architecture and engineering standards for Applied AI systems to maximize reuse, reliability, and impact across multiple product areas.
• Partner with business sponsors to translate high‑value opportunities into roadmaps and shipped products with clear success metrics and measurable outcomes.
• Build a holistic view of AI investments by collaborating with adjacent engineering groups implementing AI in their domains, aligning patterns, reusing components, and avoiding duplication.
• Drive continuous improvement in AI methodologies and best practices; evaluate emerging capabilities and land them as secure, production‑grade systems.
• Collaborate with stakeholders to embed robust governance, privacy, security, safety, and reporting practices across the AI lifecycle.
• Champion AI literacy, enablement, and adoption through demos, guidance, and technical leadership across the organization.
• Establish rigorous evaluation, guardrails, and monitoring practices; instrument offline and online metrics to ensure quality, safety, and SLOs.

• BS/MS/PhD in Computer Science or a related field, or equivalent experience.
• 10+ years of software engineering experience, with a proven track record delivering complex, production‑grade systems.
• Deep technical expertise in AI/ML, with hands‑on experience building and deploying systems using language models, retrieval/grounding (RAG), embeddings/vector search, and evaluation frameworks.
• Hands‑on experience building and scaling agentic AI systems in production environments.
• Strong experience designing and implementing evaluation systems, including LLM‑as‑Judge frameworks, metric design, synthetic data generation, and agent benchmarking pipelines.
• Proven ability to establish feedback loops from production systems into evaluation and model improvement workflows.
• Expertise in AI/LLM observability and tracing, including instrumentation of systems and analysis of trace data for performance, latency, and correctness (e.g., Open Telemetry‑based tools such as Lang Fuse or equivalent).
• Experience architecting and deploying enterprise‑scale AI systems or subsystems, with the ability to define technical direction, architecture, and reusable platform components across teams.
• Deep expertise in at least one of the following areas:
• Agent memory systems (context management, long‑term persistence, retrieval optimization).
• AI gateways / tool orchestration layers (e.g., MCP, service integration, authorization, tool discovery).
• Agentic workflows and orchestration (multi‑step planning, tool calling, error recovery, concurrency).
• Demonstrated ability to translate ambiguous problems into scalable AI systems with measurable impact.
• Experience driving engineering standards, improving system reliability, observability, and performance (latency, throughput, cost).
• Strong familiarity with security, privacy, compliance, safety, and…