SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 192,000 - 272,000 / annual
Lila Sciences is building Scientific Superintelligence to solve major scientific challenges. They are establishing a dedicated AI Safety team to identify and mitigate risks from advanced scientific AI systems while preserving core discovery capabilities.
In this Staff Software Engineer role, you will own the engineering foundation for the AI Safety team. You'll build shared software infrastructure that enables researchers, domain scientists, and safety colleagues to understand and reduce risks from scientific AI systems. Your work will span threat modeling, evaluations, red teaming, and mitigation development—turning research needs into reliable, maintainable tools.
Key responsibilities include:
- Building reusable services, libraries, and model/tool integrations that make evaluations, red-teaming campaigns, and mitigation experiments repeatable and scalable
- Developing applications that help researchers organize evidence, inspect results, review data, and investigate failures
- Partnering with safety researchers to understand evolving needs, identify shared engineering priorities, and translate research workflows into maintainable software
- Designing and maintaining data pipelines and experiment records that preserve datasets, taxonomies, model versions, configurations, and results—ensuring findings are traceable and comparisons reproducible
- Owning reliability and usability of shared safety tools through testing, debugging, monitoring, documentation, and continuous improvement
- Collaborating with core AI and software engineering teams to share tooling, align infrastructure, and avoid duplication
This is a high-impact role at the intersection of AI engineering and safety research. You'll work across the organization to support scientific discovery while building systems that help the company understand and mitigate risks from superintelligent systems.
Requirements:
- Proven track record of independently delivering and maintaining production software, including projects with ambiguous or changing requirements
- Strong Python and backend engineering skills, with experience designing APIs, working with databases, and building dependable data or execution pipelines
- Experience translating needs of researchers, domain experts, or other technical users into usable tools; comfort working across services and interfaces
- Sound engineering judgment in system design, testing, and debugging, with practical decisions about reliability, performance, and complexity
- Engineering experience in AI research, AI safety, scientific computing, or similar settings with rapidly evolving experimental workflows
- Clear communication and genuine interest in scientific AI safety, with ability to understand research context and make informed engineering decisions
Bonus qualifications:
- Experience building safety-specific tooling
- Full-stack internal applications, annotation/review tools, or systems for managing experimental evidence
- Distributed experiment execution, model-serving integrations, or isolated environments for agent evaluations
