Zep is building the long-term memory layer for the LLM application stack. Zep's open source project has seen 2K+ GitHub stars and 400K+ installs. Zep is in use at both enterprises and startups, such as Mattel, WebMD, and Athena Intelligence.

About the Role

Zep is building the long-term memory layer for the LLM application stack. We have a large and active open-source community and recently launched our cloud service. We’re seeking an experienced Full Stack Web Developer to join our startup. As a critical member of our small, fast-paced team, you will design, implement, and maintain our Go-based APIs.

We are a remote-first organization. Zep is funded by YC, Engineering Capital, and angels such as Guillermo Rauch (Vercel).

Key Responsibilities:

• Own and drive full-stack development projects from conception to deployment
• Make critical technical decisions that will influence the direction of our product
• Collaborate closely with founders and other team members to define and implement features
• Implement best practices for code quality, security, and performance

Required Qualifications:

• Passionate about AI and its potential to create innovative solutions
• Bachelor's degree in Computer Science, Software Engineering, or equivalent experience
• Minimum of 5 years of experience as a Full Stack Engineer
• Strong proficiency in TypeScript and modern JavaScript frameworks
• Familiarity with cloud services (AWS, Azure, or Google Cloud)
• Experience owning the full development cycle of a project from inception to production
• Comfortable with ambiguity and thrives in a fast-paced, evolving environment
• Passionate about AI and its potential to create innovative solutions

Nice to Have Qualifications:

• Expertise in server-side technologies and database management
• Expertise in at least one frontend framework such as React or Svelte
• Previous experience in a startup environment
• Experience with Go and Python

Benefits

• Directly impact the development of the future LLM application stack
• Competitive salary and equity compensation
• Flexible work hours and remote work options
• Health, dental, and vision insurance
• Opportunities for professional growth and development
• Collaborative and inclusive work environment

Low-latency inference is key for our offering. We use custom, fine-tuned models running in our own VPCs to power features such as real-time classification, and fact and schema-ed data extraction.

Our API is built in Go. Our web app in TypeScript and Svelte, and we offer Python, TypeScript, and Go SDKs.