Lila Sciences
Research Scientist / Research Engineer, Automated Safety
$180K–$298K
Cambridge, MA USA +5 · Full-time · Posted Oct 21, 2026
- Location
- Cambridge, MA USA
London, UK
San Francisco, CA USA
Alewife, Cambridge, MA
Europe
San Francisco, CA
About the job
Develop research methods and tools to evaluate and mitigate misuse and other safety risks in increasingly autonomous scientific AI systems.
What you'll do
- Develop and run capability evaluations and automated red-team tests for scientific models, agents, and tool-mediated workflows.
- Build reproducible experiments and tools to investigate failure modes and assess the coverage and reliability of evaluations.
- Collaborate with risk researchers and mitigation engineers on safety automation, safeguards, monitoring, and verification.
What they ask for
- 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 with domain specialists.
- For the Research Scientist profile, evidence of developing research questions, methods, and experiments; for the Research Engineer profile, evidence of building reliable research software, evaluation infrastructure, or agent systems.
Nice to have
- Automated red teaming, adversarial testing, or evaluation-method research.
- Scientific AI, tool-using agents, laboratory automation, safety monitoring, model-based evaluators, or scalable experimental infrastructure.
Pay
$180,000 — $298,000 USD (base salary)
AI focus
Safety research and automation for scientific AI, including misuse evaluations, automated red teaming, safeguards, monitoring, and oversight of increasingly autonomous systems.
Model-written summary · the original posting is authoritative