Member of Technical Staff, Applied AI Engineer, Agents

About the role

We're looking for an engineer to join the team responsible for building Edison's AI agents. This team owns the development and design of our AI scientist agent, Kosmos. You'll own the development and maintenance of production agents, prototype new capabilities with our internal science and engineering teams, and shape how our platform evolves.

Responsibilities

• Architect, implement, and maintain the AI agents that power Edison's platform, from prototype through production.
• Work with our internal science and engineering teams to explore new agent architectures, prompting strategies, tool integrations, and evaluation frameworks.
• Develop reusable infrastructure – agent skills, tool-use pipelines, benchmarks – that improves every agent on the platform.
• Spend time with R&D partners (~30%) to understand their workflows, test what you've built in real environments, and bring insights back to the team.
• Translate field insights and internal research into product direction – help the team prioritize what to build next.

Qualifications

• Typically, 5+ years of professional software engineering experience, with production experience shipping systems that real users depend on.
• Experience building LLM-powered tools or applications: prompting, context engineering, agent architectures, evaluation frameworks.
• Strong engineering foundation in Computer Science, Software Engineering, Mathematics, Physics, Data Science, or a related technical field.
• Proficiency in Python and/or TypeScript, with comfort picking up new tools and frameworks quickly.
• Able to work across engineering, science, and product teams.
• Comfortable building from scratch, driving clarity in ambiguous situations, and wearing multiple hats.

Bonus points

• Experience in life sciences, biomedical research, scientific computing, or technical R&D workflows.
• Experience building agent systems, tool-use pipelines, or evaluation/benchmarking frameworks for AI applications.
• Contributions to open-source scientific or AI tooling.