Co-Op, AI Security

Lila Sciences is building the world's first scientific super intelligence platform. As AI agents and automated systems handle more of the research and operations workload, securing them has become a core focus for the IT & Security team.

This Co-Op role focuses on the AI side of that work. You will join the IT & Security team and contribute to projects that evaluate, harden, and monitor the AI tools, agents, and automation pipelines Lila depends on. Expect exposure to areas most academic programs don't cover yet: agent governance, prompt-level threats, model deployment risks, and AI-driven security automation.

The role is structured for someone curious, technical, and looking to build applied experience. You will own specific projects, work alongside security engineers, and finish the term with hands-on work in a domain that is still being defined.

• Assist in identifying and analyzing AI/ML security vulnerabilities, including prompt injection attacks, model poisoning, and data poisoning risks
• Participate in threat modeling exercises for AI systems and recommend security mitigations
• Review and test AI/ML application code and configurations for security issues
• Research emerging AI security threats and compile findings into technical documentation
• Develop and run security tests and proof-of-concepts for AI model robustness
• Collaborate with cross-functional teams including ML engineers, product managers, and security architects

• Currently enrolled in a Computer Science, Cybersecurity, Information Security, or related program.
• Foundational understanding of cybersecurity concepts: authentication, encryption, network basics.
• Basic familiarity with how large language models and AI agents work.
• Comfortable scripting in Python or a similar language.
• Clear written communication for documenting security findings.
• Strong attention to detail and willingness to dig into unfamiliar systems.

• Coursework or projects involving AI/ML security, adversarial ML, or LLM red-teaming.
• Exposure to cloud platforms (AWS, GCP, or Azure) and their security primitives.
• Familiarity with security tooling: SIEMs, EDR, or vulnerability scanners.
• Hands-on experience building or breaking AI agents, prompt pipelines, or RAG systems.

Lila Sciences is building Scientific Superintelligence™ to solve humankind's greatest challenges. We believe science is the most inspiring frontier for AI. Rather than hard-coding expert knowledge into tools, LILA builds systems that can learn for themselves.

LILA combines advanced AI models with proprietary AI Science Factory™ instruments into an operating system for science that executes the entire scientific method autonomously, accelerating discovery at unprecedented speed, scale, and impact across medicine, materials, and energy. Learn more at www.lila.ai.

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 sounds like an environment you'd love to work in, even if you don't meet every qualification listed above, we encourage you to apply.

Lila Sciences is committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity or Veteran status.

Information you provide during your application process will be handled in accordance with our Candidate Privacy Policy.

Lila Sciences does not accept unsolicited resumes from any source other than candidates. The submission of unsolicited resumes by recruitment or staffing agencies to Lila Sciences or its employees is strictly prohibited unless contacted directly by Lila Science’s internal Talent Acquisition team. Any resume submitted by an agency in the absence of a signed agreement will automatically become the property of Lila Sciences, and Lila Sciences will not owe any referral or other fees with respect thereto.