Staff / Principal Research Engineer, AI Safety, Technical Mitigations
AI summary of the role
Lead the design and deployment of technical safety systems for Lila's scientific superintelligence platform, integrating frontier-class language models with lab automation.
What you’ll do
- Set the build and research strategy for Lila’s safety systems across scientific data pipelines, safety post-training, refusal classifiers, automated red-teaming, and monitoring systems.
- Conduct initial safeguards experimentation and buildout for Lila’s specific scientific needs, then lead a small team to execute the build and research agenda.
- Lead safety systems research to iterate beyond state-of-the-art for both in silico and lab-based scientific workflows.
- Partner closely with safety team domain experts and non-safety teams (core AI, lab automation, product) to contribute to broader research efforts.
What you’ll bring
- Track record of building safety systems, classifiers, or conducting post-training for frontier-class problems (science, reasoning, programming, etc.).
- 4-6+ years working in technical engineering with ML systems.
- Experience building scalable, production systems, not just prototypes.
- Demonstrated ability to set research directions for open problems in post-training, classifier buildouts, and other relevant systems.
Technologies
safety systems · classifiers · post-training · refusal classifiers · red-teaming · monitoring systems · ML systems · production systems · scientific data pipelines · automated safety-testing
About Lila Sciences
Autonomous AI platform that executes the scientific method end-to-end—from hypothesis generation to experimental execution—for biotech, materials, and chemical R&D.
Series A
Source and classification
Internal deployment & tooling · Evidence for this classification:
Your Impact at LILA We're building a talent-dense, high-agency AI safety team at Lila that will engage all core teams within the organization (science, model training, lab integration, etc.), to prepare for risks from scientific superintelligence. The initial focus of this team will be to build and implement a bespoke safety strategy for Lila, tailored to its specific goals and deployment strategies. This will involve technical safety strategy development, broader ecosystem engagement, safety-focused evaluations, safety systems to mitigate risks, and a safety research agenda that explores longer-term needs such as oversight of superintelligent scientific systems. We’re seeking a Technical Mitigations Lead, to lead the build out of safety systems at Lila for the safe deployment of our scientific capabilities to the world. Given the novelty of Lila’s workflows, integrating
More from the job description
Your Impact at LILA We're building a talent-dense, high-agency AI safety team at Lila that will engage all core teams within the organization (science, model training, lab integration, etc.), to prepare for risks from scientific superintelligence. The initial focus of this team will be to build and implement a bespoke safety strategy for Lila, tailored to its specific goals and deployment strategies. This will involve technical safety strategy development, broader ecosystem engagement, safety-focused evaluations, safety systems to mitigate risks, and a safety research agenda that explores longer-term needs such as oversight of superintelligent scientific systems. We’re seeking a Technical Mitigations Lead, to lead the build out of safety systems at Lila for the safe deployment of our scientific capabilities to the world. Given the novelty of Lila’s workflows, integrating frontier-class language models with narrow scientific tools and lab-based automation, this role will require the design and deployment of technical safeguards beyond the current state-of-the-art. We expect the person in this role to start off the initial mitigations build-out, and then slowly build a team to support this function. What You'll Be Building Set the build and research strategy for Lila’s safety systems, across scientific data analysis and generation pipelines, safety post-training, refusal cla [... source excerpt omitted ...] ng post-training for frontier-class problems - science, reasoning, programming, etc. 4-6+ years working in technically engineering with ML systems. Experience building scalable, production systems, not just prototypes. Demonstrated ability to set research directions for open problems in post-training, classifier buildouts, and other relevant systems. Ability to communicate complex technical concepts and concerns to non-expert audiences effectively. Bonus Points For Experience in developing or applying ML to biological or physical sciences Experience in building safeguards for scientific risks for frontier models / narrow scientific tools. Demonstrated ability to lead teams
Employer postings · Data from · Sources