Staff Software Engineer, AI Safety
$192k - $288k • Cambridge, MA USA; London, UK; San Francisco, CA USA • Full-time
Posted 15d ago
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Engineer
About the job
Lila Sciences is building a talent-dense, high-agency AI safety team focused on identifying and mitigating risks from scientific superintelligence while preserving scientific discovery capabilities. The team will develop and implement a bespoke safety strategy, encompassing technical strategy, ecosystem engagement, safety evaluations, risk mitigation systems, and research into long-term oversight needs. You will build shared software to help the team understand and reduce societal risks from scientific AI, translating needs from threat modeling, evaluations, red teaming, and mitigation development into reliable tools and systems. This role involves owning engineering work from scoping and prototyping through deployment and improvement, supporting research across scientific models, agents, and automated experimentation.
Responsibilities
- Build reusable services, libraries, and model/tool integrations for repeatable evaluations, red-teaming, and mitigation experiments.
- Develop applications to help researchers and experts organize evidence, inspect results, review data, and investigate failures.
- Collaborate with safety colleagues to understand research needs and translate evolving workflows into maintainable software.
- Build data pipelines and experiment records for traceability and reproducibility of datasets, model versions, configurations, and results.
- Ensure the reliability and usability of shared safety tools through testing, debugging, monitoring, and documentation.
- Collaborate with core AI and software engineering teams to share tooling and align on infrastructure.
Requirements
- Proven track record of independently delivering and maintaining production software, including projects with ambiguous requirements.
- Strong Python and backend engineering skills, including API design, database experience, and building dependable data or execution pipelines.
- Experience translating technical user needs into usable tools and working across services and interfaces.
- Sound engineering judgment in system design, testing, and debugging, considering reliability, performance, and complexity.
- Engineering experience in AI research, AI safety, scientific computing, or similar rapidly evolving experimental environments.
- Clear communication skills and an interest in scientific AI safety, with the ability to understand research context and make informed engineering decisions.
Benefits
- Competitive base compensation with bonus potential
- Generous early-stage equity
- Comprehensive medical, dental, and vision coverage (U.S.)
- Employer-paid life and disability insurance (U.S.)
- Flexible time off with generous company holidays (U.S.)
- Paid parental leave (U.S.)
- Educational assistance program (U.S.)
- Commuter benefits, including bike share memberships (U.S.)
- Company subsidized lunch program (U.S.)
- Regionally tailored benefits programs for international employees