Full Stack Engineer, AI
Summary
Build end-to-end product features connecting Next.js frontends with Python/Node.js backends and LLM-powered AI inference pipelines, designing autonomous agent workflows with a focus on reliability and real-time interaction.
We are seeking a Full Stack Engineer - AI to build the product layer that translates core intelligence capabilities into usable, production-grade workflows. This role encompasses designing how autonomous agents operate, handle failures, execute recovery sequences, and deliver consistent, dependable value to users across every interaction.
You will engineer end-to-end product features spanning frontend interfaces, backend orchestration services, and deep AI integrations, ensuring seamless operation under real-world conditions.
Core Responsibilities
- End-to-End Product Engineering: Architect and build robust features across the entire stack, connecting modern frontend clients with backend services and AI inference pipelines.
- Agent Workflow Design: Design sophisticated agent workflows capable of managing multi-step planning, tool utilization, failure detection, and automated recovery across sessions.
- LLM & Tool Integration: Integrate large language models, persistent memory layers, and external software tools into cohesive systems that behave reliably in production.
- Real-Time AI Interaction: Build responsive, real-time user interfaces supporting streaming responses, partial results, and strict latency constraints.
- Reliability & Observability: Continuously improve system reliability, monitoring, observability, and fallback mechanisms for non-deterministic model components.
- Cross-Functional Collaboration: Partner closely with machine learning, backend, and product teams to ship high-impact features seamlessly.
Ideal Experience & Background
- Full Stack Proficiency: Strong, demonstrated experience in full-stack engineering across modern frontend and backend frameworks.
- System Architecture: Solid understanding of scalable system design, distributed patterns, and robust API architecture.
- AI & LLM Application Experience: Practical experience working with large language models, retrieval-augmented generation (RAG) systems, or AI-powered product applications.
- Pragmatic Decision-Making: Demonstrated ability to navigate ambiguity, exercise strong technical judgment, and make pragmatic engineering tradeoffs.
- Ownership & Execution: Strong sense of ownership with a proven track record of taking complex features from initial concept through to production deployment.
Technical Stack
- Frontend: Next.js
- Languages: Python, Node.js
- Machine Learning & Frameworks: PyTorch, OpenAI API, Anthropic API, Open-Source LLMs
- Data Stores: SQL and NoSQL database systems
- Infrastructure & Orchestration: Kubernetes, Docker