Staff Agent R&D Engineer

Why Work at Lenovo

We are Lenovo. We do what we say. We own what we do. We WOW our customers.

Lenovo is a US$83 billion revenue global technology powerhouse, ranked #153 in the Fortune Global 500, and serving millions of customers every day in 180 markets. Focused on a bold vision to deliver Smarter Technology for All, Lenovo has built on its success as the world’s largest PC company with a full-stack portfolio of AI-enabled, AI-ready, and AI-optimized devices (PCs, workstations, smartphones, tablets), infrastructure (server, storage, edge, high performance computing and software defined infrastructure), software, solutions, and services. Lenovo’s continued investment in world-changing innovation is building a more equitable, trustworthy, and smarter future for everyone, everywhere. Lenovo is listed on the Hong Kong stock exchange under Lenovo Group Limited (HKSE: 992) (ADR: LNVGY).

This transformation together with Lenovo’s world-changing innovation is building a more inclusive, trustworthy, and smarter future for everyone, everywhere. To find out more visit www.lenovo.com, and read about the latest news via our StoryHub.

Description and Requirements

We are hiring an Agent R&D Engineer to develop and optimize core agent capabilities for real-world business scenarios. You will conduct algorithm research and engineering implementation, build and iterate large language model-based agents, and deliver reliable, high-performance AI solutions. This role combines academic research with engineering delivery, covering research areas including natural language processing, machine learning, deep learning, and agent development & orchestration.

Key Responsibilities

Design and develop the backend architecture for LLM Agents, including task planning, tool invocation, iterative Agent Loop, session and task state management, and execution result feedback.

Develop the full on-device NLU pipeline, including query rewriting, multi-intent splitting, context management, multi-turn dialogue, intent classification, slot extraction, normalization and post-processing.

Build the orchestration pipeline, integrate intent routing, and design hybrid decision and orchestration mechanisms combining rules, classification models and LLMs, balancing task complexity, latency, security and result controllability.

Implement multi-step reasoning and execution workflows for complex tasks. Incorporate external service or on-device execution results into subsequent decision-making to support scenarios such as device control.

Job Requirements

• Bachelor’s degree or above in Computer Science, Artificial Intelligence or other related technical fields. 5+ years of R&D experience in NLU and dialogue systems, or 3+ years of experience in LLM, agent and LLM application development.
• Proficient in at least two of Java, Go and Python, with capabilities in engineering implementation and production troubleshooting.
• Hands-on experience building LLM Agents. Solid understanding of prompt engineering, Function Calling, Tool Calling and Agent Loop.
• Strong capabilities in system design, troubleshooting and cross-team collaboration. Able to independently take charge of core technical pipelines or complex subsystems.