Fullstack Engineer – AI Systems

About the Role

We are looking for a Fullstack Engineer – AI Systems to build the product layer that transforms raw model capabilities into reliable, production-grade workflows. In this role, you will design and develop AI-powered systems that can plan, execute, recover from failures, and consistently deliver value to users across complex, multi-step tasks.

Core Focus & Responsibilities

• End-to-End Feature Delivery: Build and ship features across the frontend, backend, and AI integration layers.
• Agent Workflow Design: Design and implement agent workflows capable of planning, using tools, handling failure modes, and recovering across multi-step tasks.
• AI & Tool Integration: Integrate LLMs, persistent memory, and external tools into reliable systems that perform consistently under real-world conditions.
• Real-Time Interaction UX: Build responsive AI experiences with streaming responses, partial results, and demanding latency requirements.
• Reliability & Observability: Strengthen system reliability, monitoring, observability, error handling, and fallback mechanisms.
• Cross-Functional Collaboration: Work closely with ML, backend, and product teams to take features from initial concept through production.
• Continuous Iteration: Rapidly iterate and improve AI systems based on real-world usage, performance data, user feedback, and observed failure modes.

What We’re Looking For

• Full Stack Foundation: Strong full stack engineering experience across both frontend and backend development.
• System Design: Solid understanding of system architecture, API design, distributed systems, and scalable integrations.
• AI & LLM Experience: Hands-on experience building or integrating LLM-powered applications, RAG systems, AI agents, or other AI-driven product features.
• Pragmatic Ownership: High degree of ownership, with the ability to take ambiguous ideas from concept to production independently while making sound engineering trade-offs.
• Agility: Comfortable working in fast-moving environments with evolving requirements, rapid iteration, and a high degree of autonomy.

Tech Stack

• Frontend & Backend: Next.js, Node.js, Python
• AI & ML Frameworks: PyTorch, OpenAI, Anthropic, and open-source LLMs
• Databases: SQL & NoSQL
• Infrastructure & DevOps: Docker, Kubernetes

Expected Outcomes

• Goal-Driven Workflows: Ship AI-native product features that evolve beyond simple chat interfaces into persistent, goal-oriented workflows.
• Reliable Agent Execution: Build and deploy agent workflows that reliably complete complex, multi-step tasks across external tools and sessions.
• Performance & Fallbacks: Reduce latency and improve responsiveness while maintaining robust fallback and recovery mechanisms for LLM, API, or tool failures.
• System Abstractions: Establish clean architectural patterns and reusable abstractions for integrating LLMs, memory, external APIs, and tools into scalable product systems.

How We Work & Application Process

We are a small, world-class team with a high talent density. We make decisions collectively, move at a rapid pace, and balance high-quality execution with continuous learning and experimentation.

• Interview Process: If there appears to be a mutual fit, we will schedule 3–4 interviews with members of the technical team, conducted virtually and/or on-site. We prioritize transparency and efficiency and aim to make timely, well-informed decisions throughout the process.