AI Researcher (Agentic AI System Architecture)

GenScript ProBio•Piscataway, NJ

7h•Onsite

About The Position

GenScript Biotech Corporation (Stock Code: 1548.HK) is a global biotechnology group. Founded in 2002, GenScript has an established global presence across North America, Europe, the Greater China, and Asia Pacific. GenScript's businesses encompass four major categories based on its leading gene synthesis technology, including operation as a Life Science CRO, enzyme and synthetic biology products, biologics development and manufacturing, and cell therapy. GenScript is committed to striving towards its vision of being the most reliable biotech company in the world to make humans and nature healthier through biotechnology.

Requirements

Master’s degree or above in Computer Science, Artificial Intelligence, Cognitive Science, or related fields
3+ years of AI-related research or development experience, with hands-on experience in Agentic AI and LLM application architecture
Publications in top-tier conferences (NeurIPS, ICML, ACL, EMNLP, etc.) are preferred
Proficient in Python, familiar with asynchronous programming, concurrency control, and performance optimization
Familiar with mainstream LLM frameworks (LangChain, LlamaIndex, AutoGen, CrewAI, etc.)
Experience in large-scale distributed system design and implementation
Familiar with containerization technologies such as Docker and Kubernetes
Deep understanding of Transformer architecture and large model principles
Familiar with Prompt Engineering, Function Calling, Tool Use, and related technologies
Experience in RAG system development, familiar with vector retrieval, text Embedding, re-ranking, and related techniques
Understanding of reinforcement learning fundamentals; experience with RLHF, DPO, and related methods is a plus
Capable of system architecture design, able to independently complete technical solution design for complex modules
Familiar with design patterns and software engineering best practices
Good habits in technical documentation writing
Ability to conduct independent technical research, responsible for the entire process from problem definition to solution implementation
Strong literature reading and summarization skills, able to quickly absorb cutting-edge research achievements
Capability in technology selection and evaluation, able to make reasonable decisions among multiple solutions
Strong passion for AI technology, keeping up with the latest developments in the Agentic AI field
Excellent communication and collaboration skills, able to work efficiently with engineering teams
Critical thinking ability, capable of objectively evaluating and iteratively optimizing technical solutions

Nice To Haves

Contributions to Agent framework open-source projects (e.g., LangChain, AutoGen, LlamaIndex)
Production-level Agent system deployment experience with 10,000+ daily task processing
Familiarity with cognitive science and human decision-making theory, able to apply them to Agent architecture design
Research experience in Embodied AI or robotics
Familiarity with Graph Neural Networks, Knowledge Graphs, and related project experience
Entrepreneurial experience or experience building AI products from 0 to 1

Responsibilities

Harness Architecture Design & Implementation: Research and design Agent execution framework, providing standardized runtime environment for intelligent agents. Implement tool call orchestration mechanism, supporting unified abstraction for function calling, API integration, and external system interaction. Build execution sandbox environment to ensure safety and controllability of Agent operations. Design task decomposition and planning engine, supporting automatic breakdown of complex goals and execution path optimization. Implement execution state tracking and anomaly recovery mechanisms to ensure reliability of long-running tasks.
Memory System Architecture Development: Design hierarchical memory architecture, covering storage and retrieval mechanisms for working memory, short-term memory, and long-term memory. Research memory compression and summarization techniques, enabling efficient storage of massive interaction history while preserving key information. Build context-aware memory system, supporting multi-dimensional memory association based on time, task, and user. Develop memory retrieval augmentation mechanisms, achieving deep integration of RAG and Agent memory. Explore memory forgetting and update strategies, balancing memory capacity with information timeliness.
Multi-Agent Collaboration Architecture: Research multi-Agent system architecture, design communication protocols and collaboration mechanisms between Agents. Implement role specialization and task allocation algorithms, supporting orchestration of expert Agents, coordinator Agents, executor Agents, and other roles. Build consensus achievement and conflict resolution mechanisms to handle decision disagreements among multiple Agents. Design Agent social behavior norms, simulating communication, negotiation, and feedback patterns in human team collaboration. Explore emergent behavior and collective intelligence, researching self-organization and adaptive capabilities in multi-Agent systems.
General Architecture Capabilities: Design Agent evaluation and benchmarking system, establishing quantitative capability metrics. Build Agent behavior interpretability framework, supporting decision process tracing and attribution analysis. Research Agent safety alignment mechanisms to prevent risks such as unauthorized operations, harmful outputs, and goal drift. Track cutting-edge Agentic AI research and translate academic achievements into engineering practice.