Member of Technical Staff, Agent Engineer
Edison ScientificBase Salary
$175k - $240k/yr
Responsibilities
- Architect, implement, and maintain production AI agents from prototype through deployment.
- Prototype agent architectures, prompting strategies, tool integrations, and evaluation frameworks.
- Develop reusable agent skills, tool-use pipelines, benchmarks, and infrastructure.
- Spend approximately 30% of the time with R&D partners to understand workflows and validate agent capabilities.
- Translate field insights and internal research into product direction and prioritization.
- Collaborate across engineering, science, and product teams.
Requirements
- Typically 4+ years of professional software engineering experience, including production systems used by real users.
- Experience building LLM-powered tools or applications involving prompting, context engineering, agent architectures, or evaluation frameworks.
- Strong foundation in computer science, software engineering, mathematics, physics, data science, or a related technical field.
- Proficiency in Python and/or TypeScript.
- Ability to work across engineering, science, and product teams and operate effectively in ambiguous, fast-moving environments.
Benefits
- Competitive salary and equity.
- Full healthcare coverage with 100% of premiums paid for employees and dependents.
- Yearly new parent stipend and fertility coverage through Carrot.
- Mental health support through Rula.
- Twelve weeks of paid parental leave for maternity, paternity, and adoption.
- Yearly employer-funded pet care stipend.
- Commuter benefits for transit and parking using pre-tax dollars.
- 401(k) company matching.
- $300 quarterly health and wellness benefit.
- Free lunch on office days and dinner when working late.
- Regular team off-sites and company events.
Tech Stack
Categories
About Edison Scientific
Edison Scientific is building the AI platform for scientific research and development. Kosmos, our AI scientist, collaborates with teams across the full R&D lifecycle, leveraging proprietary data and organizational context to help navigate complex scientific decisions and accelerate timelines from discovery to FDA approval. We believe the full gains from AI in science will only be realized when AI systems are integrated across the entire research and development stack, continuously learning from the evolving scientific context inside an organization. With Edison Scientific, scientists and researchers remain at the center of scientific progress, using AI to amplify their expertise and accelerate discovery at unprecedented speed. Edison is a scientist-led company that was spun out of the nonprofit research lab FutureHouse in 2025, backed by $70M from Spark Capital, Triatomic Capital, Susa Ventures, Pillar Ventures, among other investors.