Full Stack Engineer

About the Opportunity

We are seeking a Full Stack Engineer to build end-to-end AI product features within our artificial intelligence organization. You will design agent workflows that manage multi-step planning, tool use, failure, and recovery for reliable real-world applications.

Responsibilities:

• Develop full-stack features integrating frontend, backend, and advanced AI components using technologies like Next.js, Node.js, Python, Pytorch, and OpenAI/Claude APIs.
• Design resilient agent workflows capable of handling complex multi-step tasks with robust fallback mechanisms and real-time streaming interactions.
• Integrate large language models (LLMs), memory systems, retrieval-augmented generation (RAG), and external tools into scalable product features.
• Enhance system reliability through observability improvements and failure analysis based on usage data.
• Collaborate cross-functionally with ML, backend, and product teams to deliver production-ready AI experiences from concept to deployment.

Requirements:

• Strong expertise in artificial intelligence and full-stack engineering across modern frontend and backend ecosystems.
• Solid understanding of system design, API architecture (REST/gRPC), and cloud infrastructure including Docker and Kubernetes.
• Proven experience with LLMs, RAG systems, NoSQL/SQL databases, and frameworks like Pytorch.
• Ability to navigate ambiguity and make pragmatic engineering decisions in fast-paced environments.