AI Researcher (Agentic AI System Architecture)

GenScript/ProBio•Piscataway, NJ

8h•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
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
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

Publications in top-tier conferences (NeurIPS, ICML, ACL, EMNLP, etc.) are preferred
Experience with RLHF, DPO, and related methods is a plus
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: Responsible for designing and implementing Agent execution frameworks, tool call orchestration, execution sandbox environments, task decomposition and planning engines, and execution state tracking/anomaly recovery mechanisms.
Memory System Architecture Development: Responsible for designing hierarchical memory architectures, researching memory compression and summarization, building context-aware memory systems, developing memory retrieval augmentation mechanisms, and exploring memory forgetting/update strategies.
Multi-Agent Collaboration Architecture: Responsible for researching multi-Agent system architectures, implementing role specialization and task allocation algorithms, building consensus achievement and conflict resolution mechanisms, designing Agent social behavior norms, and exploring emergent behavior and collective intelligence.
General Architecture Capabilities: Responsible for designing Agent evaluation and benchmarking systems, building Agent behavior interpretability frameworks, researching Agent safety alignment mechanisms, and tracking/translating cutting-edge Agentic AI research into engineering practice.