Research Engineer

Requirements

• We are looking for a creative and rigorous engineer who is passionate about using AI as a tool to understand the human world.
• (Desirable) Experience or strong interest in multi-agent systems, agent-based modeling (ABM), or game theory.
• MS or PhD in Computer Science, Machine Learning, Computational Social Science, or a related quantitative field, or equivalent practical experience.
• (Desirable) Hands-on experience with advanced LLM application techniques like RAG, chain-of-thought, and agentic tool use.
• Deep experience in applying large language models (LLMs) to solve complex, open-ended problems.
• (Desirable) Experience designing and conducting experiments in a social science or human-computer interaction (HCI) context.
• Strong proficiency in Python and common ML libraries/frameworks (e.g., PyTorch, JAX, TensorFlow, Hugging Face).
• (Desirable) A track record of publications in relevant AI or interdisciplinary conferences.
• A strong scientific mindset geared towards rigorous experimentation, coupled with the engineering discipline to build reliable and scalable systems to test complex hypotheses.
• (Desirable) Experience deploying ML-driven applications into production environments.
• A keen interest and/or background in principles of human behavior, cognitive science, psychology, or social dynamics.
• Excellent communication skills, with the ability to articulate complex technical and experimental concepts clearly.

What the job involves

• As a Research Engineer at Electric Twin, you will focus on modeling human behavior using AI. Your primary role is to pioneer the application of existing LLMs to create believable, consistent, and scientifically-grounded AI agents.
• You will design the cognitive architecture of synthetic agents, evaluate their behavior in ambiguous scenarios, and develop experimental methods to validate our simulations. Key questions include: How can LLMs give agents persistent memory? How do we ensure a population of agents reflects real demographics? How do we measure 'realism' in the absence of ground truth?
• This interdisciplinary role combines creative AI application, rigorous experimental design, and insights from computational social science to bring synthetic populations to life.
• Design AI Agents: Develop prompting strategies, retrieval-augmented generation (RAG), and tool-use frameworks for consistent personas, memories, and reasoning.
• Develop Experimental Methods: Design experiments to test behavioral outputs of LLM-powered agents against real data and social science principles.
• Create Evaluation Frameworks: Build methods to measure the quality and realism of simulations, especially on ambiguous tasks.
• Build the Simulation Platform: Contribute to architecture enabling complex simulations with thousands of AI agents.
• Translate Needs into Research: Collaborate with product and commercial teams to address client challenges through research and technical solutions.
• Stay at the Forefront: Apply latest techniques in agentic AI, multi-agent systems, and LLM evaluation to enhance our platform's capabilities.