Agent Backend Engineer – ARK Large Model Platform (Singapore)

About the Team The Applied Machine Learning (AML) - Enterprise team provides machine learning platform products on VolcanoEngine with cloud resource scheduling system which intelligently orchestrates different tasks and jobs with minimised costs of every experiment and maximised resource utilisation, rich modelling tools including customised machine learning tasks and web IDE, and multi-framework high performance model inference services. In 2021, through VolcanoEngine, we released this machine learning infrastructure to the public, to provide more enterprises with reduced costs of computation power, lower barriers to machine learning engineering and deeper developments in AI capabilities. Responsibilities -Responsible for research and development of Agent technologies for the Volcano Engine Ark Large Model Platform, including foundational capabilities such as multi-agent frameworks and memory mechanisms -Develop domain-specific agents such as UI Agents and DeepResearch Agents to enhance large model performance in specialized scenarios -Design and implement user-friendly and efficient Agent development toolkits to lower the barrier for developers adopting Agent technologies -Explore innovative methods and technologies in the Agent domain, propose advanced paradigms, and help drive industry progress -Investigate evaluation methodologies for Agents and build a comprehensive evaluation system for the Ark Agent ecosystem Minimum Qualifications -Proficient in at least one programming language such as Python, Java, or Go -Strong understanding of large language models (LLMs), including their principles and application methods is required Preferred Qualifications: -Deep understanding of Agent-related methodologies; experience with reinforcement learning and planning algorithms is a plus -Passion for AI applications, with the ability to quickly reproduce research papers and translate them into production systems. Publications in top-tier conferences or contributions to open-source projects are a plus