Develop and run evaluations of scientific AI models, agents, and tool-mediated workflows, creating reproducible methods and tools to investigate failure modes and assess the quality of automated evaluations. Collaborate with risk researchers and mitigation engineers to improve safeguards and build broader safety automation for monitoring, evidence triage, regression testing, and risk response. Candidates need strong empirical judgment, practical programming ability, experience with modern AI systems, and the ability to investigate ambiguous failures and communicate limitations. Research Scientists should demonstrate research-question selection and defensible experimental methods, while Research Engineers should show experience building reliable research software, evaluation infrastructure, or agent systems.
Lila Sciences provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.
