PostDoc Researcher

Thank you for considering a career with the Research Foundation of The City University of New York (RFCUNY). The team at RFCUNY is made up of dedicated, talented professionals committed to providing the services that allow CUNY researchers, faculty, and staff to focus on their intellectual curiosity and scientific discoveries. We are pleased that you are interested in exploring opportunities to join RFCUNY. Primary Location: The CITY COLLEGE of NEW YORK Bargaining Unit: No The AI-Enabled Bio-Inspired Materials discovery Ecosystem (AI-BIOME) at the CUNY City College of New York (CCNY) invites applications for Postdoctoral Researchers. Funded by the NSF grant award, AI-BIOME is a new, public-private Programmable Cloud Laboratory (PCL) Node dedicated to bio-derived, supramolecular, and bioinspired materials design, discovery, and characterization. We are seeking exceptional, highly motivated early-career scientists to join our team at the frontier of artificial intelligence, robotics, and soft-matter physics. You will work directly with Lead PI/Science Lead Ronald Koder Co-PI/AI Lead Saptarashmi Bandyopadhyay Co-PI/Data Lead Raymond Tu to build a scalable, reproducible synthesis-and-characterization pipeline. Position at a Glance Role: PostDoctoral Researchers Location: CCNY The Role This position offers a unique opportunity to work at the intersection of AI agent-enabled reasoning and hands-on autonomous experimentation. Biological and bio-inspired materials offer a massive, programmable design space perfectly suited for algorithmic generalization and optimization. You will help pioneer closed-loop discovery, where multiple AI agents generate hypotheses, propose designs, autonomously plan and execute multi-step trustworthy experiments with robots, and refine themselves in real time through scientific exploration. As Postdoctoral Researchers, your key responsibilities will include: Research Integration: Conduct research integrating AI-driven experimental design with automated materials synthesis and characterization, emphasizing trustworthiness, reliability, robustness, and transparency in AI decisions that guide embedded experimental workflows. Algorithms, Theory and System-Level Research to Control AI Agents : Build robust and efficient algorithms to control AI Agents that can learn generalizable plans to design and synthesize bio-inspired materials, adapt to mistakes in the plans autonomously, steer navigation and accelerate discovery and exploration at a distributed scale. This includes developing planning, reasoning, navigation and exploration algorithms (e.g., efficient RL, imitation learning approaches like behavioral cloning, game theoretic equilibriums, hierarchical controllers, causal and probabilistic reasoning modules) that ensure trustworthy behavior of agents in autonomous laboratory environments and enable long-horizon, multi-step high-throughput experimental campaigns. Autonomous Workflow Development: Develop new workflows within the robotic platforms, focusing on training new capabilities to the robots. You will help design and validate autonomous laboratory protocols in which embedded AI agents coordinate liquid-handling robots, robotic carts, analytical instruments, and cloud infrastructure in a closed loop high-throughput experimentation environment. Scientific Publication and Communication: Disseminate scientific results to the broader community by publishing impactful research papers in reputed conferences and journals. Collaborate with PCL nodes jointly under the PCL research network. Mentorship: Supervise graduate research assistants, undergraduates and the workforce originating from the AI-BIOME PCL. Collaboration: Work alongside our expansive network of partners, including researchers at Brookhaven National Laboratory, NVIDIA, Mozilla AI and other collaborators in major National Labs and companies. Other duties as assigned. Qualifications Ph.D. in Computer Science, Machine Learning, Robotics, Electrical and Computer Engineering, Computational Materials Science, Chemical Engineering, Computational Physics, Bioengineering, Computational Chemistry, or a related discipline. Experience or strong interest in developing AI/ML algorithms and methods for Single-Agent and Multi-Agent Autonomous Decision Making (such as reinforcement learning, imitation learning, game theory, control algorithms, large multimodal models (VLMs/VLAs), or Bayesian optimization) to autonomously explore physical scientific discovery, laboratory automation, or experimental control. Experience or strong interest in hardware development, focusing on building complete hardware-software systems to accelerate discovery in material and interfacial science, including robotic platforms, embedded chemical engineering systems and automated analytical pipelines tightly integrated with AI agents and cloud-based orchestration. Ability to work independently while contributing effectively to a highly collaborati #J-18808-Ljbffr rfcuny