Full Stack AI Engineer

Our client is an AI startup building a proactive AI assistant that helps users complete real-world tasks through intelligent, goal-driven workflows.

We are looking for a Full Stack AI Engineer to build the product layer that transforms AI capabilities into intuitive, production-ready workflows. In this role, you'll design how AI agents operate, recover from failures, and consistently deliver value to users in real-world scenarios.

Responsibilities

• Build end-to-end product features across the frontend, backend, and AI integrations.
• Design agent workflows that manage planning, tool usage, failures, and recovery across multi-step tasks.
• Integrate LLMs, memory, and external tools into reliable production systems.
• Build real-time AI experiences with streaming responses, partial outputs, and low-latency interactions.
• Improve system reliability, observability, and fallback mechanisms.
• Collaborate closely with ML, backend, and product teams to deliver features from concept to production.
• Continuously iterate and improve the product based on user feedback and real-world failure patterns.

Requirements

• Strong experience in full stack development.
• Solid understanding of system design and API architecture.
• Experience building applications powered by LLMs, RAG systems, or other AI technologies.
• Ability to navigate ambiguity and make pragmatic engineering decisions.
• Strong ownership with the ability to drive features from concept to production.
• Comfortable working in fast-paced environments with evolving priorities and requirements.
• Tools and technologies: Next.js, Python, Node.js, PyTorch, OpenAI, Anthropic, Open-source LLMs, SQL, NoSQL, Kubernetes, Docker.