What You'll Do
Design and implement backend infrastructure centered around large language models, ensuring systems are robust, efficient, and production-ready. Develop intelligent agent workflows that integrate with external tools and services, enabling autonomous task execution. Build and maintain retrieval-augmented generation pipelines using vector search to enhance model accuracy and context relevance. Manage prompt orchestration and context handling across complex AI interactions. Continuously optimize for speed, cost, and reliability while deploying new AI capabilities into live products.
Requirements
- Proven experience in backend development using Node.js, TypeScript, Python, and frameworks like Nest.js
- Strong track record working with LLMs and AI APIs in production environments
- Hands-on experience building AI agents or multi-step reasoning workflows
- Familiarity with vector databases such as Pinecone or Weaviate
- Direct experience implementing RAG systems at scale
- Solid understanding of prompt engineering and system-level AI design
- Experience deploying and monitoring AI-powered services in cloud environments, particularly GCP
Benefits
- Significant ownership in a rapidly evolving AI-focused startup
- Remote-friendly work model with flexibility built into the routine
- Opportunity to shape the architecture of production-grade agent systems from the ground up
