Staff / Principal Engineer, Technical Mitigations Research
Lila Sciences is seeking a Staff or Principal Engineer to lead the development of safety systems for the deployment of our scientific capabilities. This role involves designing and implementing technical safeguards that integrate advanced language models with specialized scientific tools and lab-based automation. The successful candidate will initiate the mitigation build-out and gradually assemble a supporting team.
Key responsibilities include setting the strategy for Lila's safety systems across scientific data analysis and generation pipelines, safety post-training, refusal classifiers, automated safety-testing systems, and monitoring systems. The role also involves conducting initial safeguard experiments tailored to Lila's scientific needs, leading a small team to execute the research agenda, and advancing safety systems research beyond current standards. Collaboration with safety team members, domain-specific experts, and non-safety teams is essential, as is contributing to external communications on Lila's safety efforts.
Candidates should have a proven track record in building safety systems, classifiers, or conducting post-training for complex problems in science, reasoning, or programming. A minimum of 4-6 years of experience in engineering with machine learning systems is required, along with experience in developing scalable, production systems. The ability to set research directions for open problems in post-training and classifier development, as well as effectively communicating complex technical concepts to non-expert audiences, is crucial.
We offer competitive compensation, including bonus potential and generous early equity. The expected base salary range is $224,000 to $336,000 USD. Benefits include comprehensive medical, dental, and vision coverage; employer-paid life and disability insurance; flexible time off; paid parental leave; educational assistance; commuter benefits; and a company-subsidized lunch program.
Lila Sciences is building Scientific Superintelligence™ to solve humankind's greatest challenges. We combine advanced AI models with proprietary AI Science Factory™ instruments into an operating system for science that autonomously executes the entire scientific method, accelerating discovery across medicine, materials, and energy. Guided by our core values of truth, trust, curiosity, grit, and velocity, we move with startup speed while tackling problems of historic importance. If this environment resonates with you, we encourage you to apply.