Full Stack Engineer, AI systems

Role overview This position focuses on building the product layer for AI-native applications that bring intelligent automation to everyday workflows such as conversations, errands, and personal organization. The engineer will design how agent systems operate, fail, recover, and deliver consistent value to end users in production environments. The work spans frontend, backend, and AI integrations with an emphasis on shipping reliable, goal-driven features that move beyond simple chat.

Responsibilities - Build end-to-end product features across frontend, backend, and AI integrations - Design agent workflows that handle planning, tool use, failure, and recovery across multiple steps - Integrate LLMs, memory layers, and external tools into systems that behave reliably under real-world conditions - Implement real-time AI interactions including streaming responses, partial results, and tight latency constraints - Improve system reliability, observability, and fallback mechanisms for production AI features - Collaborate closely with ML, backend, and product teams to iterate based on real usage and failure modes

Requirements - Strong full stack engineering experience across frontend and backend - Solid understanding of system design and API architecture - Hands-on experience with LLMs, retrieval-augmented generation systems, or AI-powered applications - Ability to handle ambiguity and make pragmatic engineering decisions - Strong ownership, able to take features from idea through to production - Comfort working in fast-moving environments with evolving requirements

Nice to have - Familiarity with modern frameworks such as Next.js, Python, Node.js, and PyTorch - Experience with leading LLM providers and open-source model ecosystems - Comfort with SQL and NoSQL data stores, Kubernetes, and Docker