Research Scientist Intern, AI Agents for Autonomous Laboratories (PhD)

Meta•Published 17 hours ago•First seen 56 minutes ago

Description

At Reality Labs Research, our goal is to explore, innovate and design novel interfaces and hardware for the next generation of virtual, augmented, and mixed reality experiences. We are driving research towards a vision of natural, seamless experiences in XR environments that are effective, enjoyable, and functionally indistinguishable from those in the real world. As a Research Scientist Intern, you will work at the intersection of AI agents, laboratory automation, and wearable computing, alongside a world-leading materials innovation and discovery team. Your primary focus will be on building the software layer that lets AI agents communicate with and operate laboratory equipment, and on turning first-person capture from smart glasses, together with instrument data, into a time-aligned digital record of experiments. This work is a step toward self-driving labs, where knowledge captured from expert researchers becomes structured, executable protocols for agents and, eventually, robots. Our internships are twelve (12) to twenty-four (24) weeks long and we have various start dates throughout the year.

Responsibilities

Design and implement interfaces (for example, MCP servers, APIs, and instrument drivers) that let AI agents query status, issue commands, and retrieve data from laboratory equipment used for synthesis, characterization, and crystal growth. Develop agentic workflows that plan and run experimental steps, with safety constraints, human-in-the-loop approval, and full action logging. Build pipelines that convert first-person video, audio, and instrument telemetry from smart glasses into a synchronized experiment timeline and structured, machine-readable protocols. Apply and evaluate multimodal foundation models (vision-language, speech) to recognize lab actions, materials, and events, including failures and anomalies. Link captured procedures with characterization and process data in a searchable experiment record. Collaborate with materials scientists, chemists, and AI researchers to define requirements, test with real lab users, and measure impact. Publish research results and contribute to research that can be applied to Meta product development.

Qualifications

Currently has or is in the process of obtaining a Ph.D. degree in Computer Science, Robotics, Chemical Engineering, Chemistry, Materials Science, or relevant technical field Must obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment Research experience in at least one of the following areas: LLM-based agents and tool use, laboratory automation or self-driving labs, computer vision or multimodal learning, instrument control and data acquisition Experience building software systems in Python Intent to return to the degree program after the completion of the internship/co-op Experience with agent frameworks and tool-calling protocols, or with evaluating LLM agents Hands-on experience connecting software to lab instruments or robotic platforms Experimental lab experience in chemistry or materials science, such as synthesis, crystallization, or materials characterization Experience with egocentric video, wearable or AR devices, or time-aligning multimodal data streams Experience with electronic lab notebooks, LIMS, data schemas, or knowledge graphs for scientific data Experience with Bayesian optimization or active learning for experimental design Publications at venues such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, ICRA, IROS, CoRL, CHI, or UIST, or in journals such as Digital Discovery, Nature, Science, or JACS Experience working and communicating cross functionally in a team environment

Compensation: $7,650/month to $12,667/month + benefits