Research Scientist / Research Engineer, Automated Safety
About The Position
Lila Sciences is building an AI safety team that will work across science, model training, lab integration, and other organizational teams to identify and mitigate risks from scientific superintelligence while preserving scientific discovery capabilities. The team’s initial work includes developing a safety strategy tailored to Lila’s goals and deployment strategies, technical safety strategy development, ecosystem engagement, safety evaluations and mitigation systems, and research into longer-term needs such as oversight of superintelligent scientific systems. The role focuses initially on misuse, developing flexible and automated red-teaming approaches to test safety-relevant scientific capabilities and safeguard robustness. It also contributes to safety automation that helps evaluate, monitor, and respond to risks across increasingly autonomous scientific workflows. The person in this role will own reusable research methods and assessment tools and work with mitigation engineers implementing protective mechanisms. Responsibilities may span or evolve between the Research Scientist and Research Engineer profiles. The Research Scientist profile emphasizes selecting valuable research questions, developing or adapting methods, and designing experiments that support defensible conclusions, with the ability to prototype and test ideas. The Research Engineer profile emphasizes building reliable research software, evaluation infrastructure, or agent systems that enable reproducible experiments and efficient iteration, while contributing to experimental design and interpretation.
Requirements
- Strong empirical judgment, practical programming ability, and experience working with modern AI systems.
- Ability to investigate ambiguous failures, design informative comparisons, and communicate limitations clearly.
- Interest in scientific misuse risks and ability to collaborate productively with domain specialists.
- For the Research Scientist profile: evidence of selecting valuable research questions, developing or adapting methods, and designing experiments that yield defensible conclusions; ability to prototype and test ideas.
- For the Research Engineer profile: evidence of building reliable research software, evaluation infrastructure, or agent systems that enable reproducible experiments and efficient iteration; ability to contribute to experimental design and interpretation.
Nice To Haves
- Experience in automated red teaming, adversarial testing, or evaluation-method research.
- Experience in scientific AI, tool-using agents, laboratory automation, or other complex environments.
- Experience with safety monitoring, model-based evaluators, or scalable experimental infrastructure.
Responsibilities
- Develop and run capability evaluations of scientific models, agents, and tool-mediated workflows, including simulated lab environments, in collaboration with domain experts.
- Create methods or systems to explore diverse failure modes, adapt tests as evidence emerges, and support systematic investigation beyond fixed benchmarks.
- Build reproducible experiments and evaluation tools that capture relevant behavior, outcomes, and evidence needed to interpret findings.
- Measure the quality and coverage of automated assessments, including evaluator failure cases.
- Develop broader safety automation across threat model management, evidence triage, regression testing, monitoring workflows, and tools that help researchers assess and respond to risks.
- Collaborate with risk researchers and mitigation engineers to translate findings into improved assessments and safeguards, and verify whether changes work.
- Own reusable research methods and assessment tools for evaluating and addressing risks in increasingly autonomous scientific workflows.
Benefits
- Competitive base compensation with bonus potential and generous early-stage equity.
- For full-time U.S. employees: medical, dental, and vision coverage; employer-paid life and disability insurance; flexible time off with generous company-wide holidays; paid parental leave; educational assistance; commuter benefits, including bike share memberships for office-based employees; and a company-subsidized lunch program.
- For full-time employees outside the U.S.: a comprehensive benefits program tailored to their region.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed
