Full Stack Engineer, AI systems

Role overview Build full-stack product features that make AI agents useful in everyday communication and coordination. You’ll connect user-facing experiences with language models, memory, and external tools, shaping workflows that can plan, act across multiple steps, and recover when something goes wrong.

Responsibilities - Deliver product features across frontend, backend, and AI integrations. - Design agent workflows for planning, tool use, multi-step tasks, and recovery from failures. - Integrate language models, memory, and external services into reliable product systems. - Build responsive AI interactions that support streaming and partial results while keeping latency low. - Improve reliability through observability, evaluation, monitoring, and fallback mechanisms. - Work with product, backend, and machine learning colleagues, using real-world usage to guide iteration.

Requirements - Strong full-stack engineering experience spanning 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 decisions amid ambiguity and changing requirements. - Ownership of features from initial idea through production delivery. - Comfort working independently in a fast-moving team.

Nice to have The listed technologies include Next.js, Python, Node.js, PyTorch, SQL and NoSQL databases, Kubernetes, Docker, and commercial or open-source language models.

Benefits and work setup The team describes itself as small, hands-on, and fast-moving, with collective decision-making and an emphasis on balancing delivery with learning. The interview process typically includes three meetings and no more than four; meetings may be virtual or onsite.