AI Agent Architect & Senior Research Scientist

SLAC; Palo Alto (CA); On-site; USD 144,000 - 199,000; Full time

Job summary

Stanford Law School's liftlab seeks a Senior Research Scientist, AI Agent Architect to lead and audit AI research agents, aligning them with high‑quality scholarly standards while advancing the lab's research agenda.

You will design agent pipelines, set rigor thresholds, translate research questions into executable tasks, and coordinate with Directors and researchers to ensure reproducible results.

Qualifications

• Demonstrated record of conceiving, conducting, and producing high-quality research end to end.
• Ability to translate substantive research questions into task specifications and evaluation rubrics suitable for AI agent execution.
• Ability to audit computational research output for errors, non-reproducibility, and subtle methodological invalidity.
• Strong programming and data skills, including machine learning methods, data collection and management, and research workflow design.
• Ability to read and understand original academic research papers and their associated source code, and to replicate results from diverse fields.
• Ability to exercise independent, real-time research judgment and to communicate standards of rigor to both researchers and technology providers.

Responsibilities

• <b>Research Engagement:</b>Partner with the lab Directors to translate substantive research questions into structured problems that can be decomposed into tasks executable by AI research agents, exercising independent judgment about which steps are appropriate for agent execution and which require direct human reasoning; attend lab and research-group meetings to scope agent-assisted workflows and identify where agents can responsibly accelerate inquiry.
• <b>Solutions Development:</b>Design and orchestrate pipelines of AI research agents that execute research tasks (e.g., literature review, data collection, coding, modeling, analysis, and drafting); write the task specifications, tool integrations, and guardrails under which agents operate; audit agent output for methodological rigor, reproducibility, and error, iterating on prompts, tooling, and workflow design to correct failures and improve reliability; read original academic papers and source code to validate results agents replicate, ensuring agent-produced work meets the standard of peer-reviewed research.
• <b>Documentation and Training:</b>Create the standards, playbooks, and evaluation harnesses that allow the lab to responsibly deploy research agents, keeping them current as agent capabilities evolve; develop and deliver documentation and training on agent-assisted research methods and on auditing agent output for rigor.
• <b>Partnership and Collaboration:</b>Coordinate interactions between lab researchers and AI/technology providers; evaluate platforms and agent tooling; co-create agent capabilities with researchers and communicate infrastructure needs to data and software professionals.
• <b>Teamwork:</b>Provide guidance and direction to more junior research staff and set the working standards for the lab's hybrid human-and-AI-agent team.
• <b>Project Leadership:</b>Contribute to the design and build-out of the lab's AI-research-agent infrastructure as a flagship initiative, setting the architecture for how agents are deployed, supervised, and evaluated across projects.
• <b>Workforce and Team Management:</b>Support the management and direction of staff who engage with AI agents; represent the lab's agent-assisted research model to internal and external audiences.

Job description

Stanford Law School's liftlab seeks a Senior Research Scientist, AI Agent Architect to lead and audit AI research agents, aligning them with high‑quality scholarly standards while advancing the lab's research agenda.

You will design agent pipelines, set rigor thresholds, translate research questions into executable tasks, and coordinate with Directors and researchers to ensure reproducible results.