27 days ago
Responsibilities
- Design, implement, and deploy production-grade AI agents with multi-step reasoning and tool-calling workflows.
- Build agent harnesses for reliable production performance, including context management and lifecycle control.
- Engineer context pipelines for dynamic retrieval and semantic search within agent workflows.
- Implement production-grade reliability features such as retry logic and structured output validation.
- Develop evaluation frameworks to measure agent quality and catch regressions.
- Architect and implement scalable backend services and APIs in Go, Rust, or TypeScript/Node.js.
- Build and maintain integrations with external systems for agent functionality.
- Own deployment, monitoring, and observability using Docker and Kubernetes.
- Create functional web interfaces in React/Next.js for various applications.
- Manage features end-to-end, from requirements to ongoing maintenance.
- Apply prompt engineering rigorously as part of the development process.
Requirements
- 5+ years of professional software engineering experience with a full-stack production track record.
- Strong command of Python and/or TypeScript at a production level.
- Depth in backend engineering with Go, Rust, or TypeScript/Node.js for production services.
- Proficiency in frontend engineering with React, Next.js, and TypeScript.
- Experience with automated testing, CI/CD pipelines, and observability practices.
- Proficient in containerization and deployment using Docker and Kubernetes.
- Hands-on experience building and deploying LLM-powered systems or AI agents in production.
- Familiarity with at least one LLM API and agentic frameworks.