Full Stack Engineer, AI systems

Role overview Build the product systems that make AI agents useful and dependable in real-world workflows. You’ll work across frontend, backend, and AI integrations, shaping how agents plan, use tools, handle failures, and recover while delivering low-latency interactions that extend beyond one-off chat.

Responsibilities - Ship complete product features spanning user interfaces, services, and AI integrations. - Design multi-step agent workflows for planning, tool use, failure handling, and recovery across sessions. - Integrate language models, memory, and external tools into production systems. - Build streaming interactions with partial results and attention to response time. - Improve reliability through observability, fallback paths, evaluation, and monitoring. - Work with machine learning, backend, and product colleagues, iterating against real usage and failure patterns.

Requirements - Strong full-stack engineering experience across frontend and backend development. - Solid understanding of system design and API architecture. - Experience with language models, retrieval-augmented generation, or AI-powered applications. - Ability to make practical engineering decisions amid ambiguity and changing requirements. - Ownership of features from initial idea through production delivery. - Comfort working in a fast-moving environment.

Nice to have Experience with Next.js, Python, Node.js, PyTorch, SQL or NoSQL databases, Kubernetes, Docker, or commercial and open-source language models.

Benefits and work setup Join a small, hands-on team that makes decisions collectively and balances rapid delivery with learning. The role calls for independent execution and sound judgment. Interviews are held remotely and/or onsite, typically over three or four conversations.