Senior Full-Stack Engineer

Role Overview

Senior Full-Stack Engineer (Remote, US-based)

Build performant full-stack applications across both user interfaces and scalable backend services. This role also focuses on AI-native experiences, including LLM-powered features such as RAG and agentic workflows, and on deploying serverless solutions on AWS.

Responsibilities

• Design and develop full-stack applications
  • Node.js services and APIs on the backend
  • Responsive, polished client interfaces using Vue.js, Next.js, or similar
• Ship AI-native features end-to-end
  • LLM endpoints
  • RAG pipelines
  • Tool/function calling
  • Agentic workflows
  • Maintain reliability, observability, and cost-efficiency
• Architect and optimize serverless systems on AWS (e.g., Lambda, S3, RDS)
• Collaborate with design and product to create crisp, accessible experiences and iterate based on customer feedback
• Mentor engineers (mid-level and junior) via code reviews, design critique, and strong engineering culture
• Ensure production quality
  • Monitor, debug, and improve reliability, performance, and security
  • Include AI component behavior and AI cost/efficiency in production monitoring
• Participate in code reviews and continuous improvement and use AI coding assistants to accelerate delivery without losing rigor

Requirements

• 6+ years building full-stack applications in Node.js for production deployments
• Strong frontend skills with Vue.js, Next.js, or similar; and solid HTML5/CSS3 plus responsive design
• Hands-on experience building LLM-powered production applications, including:
  • Prompt engineering and structured output
  • Tool/function calling
  • RAG
  • Agentic workflows
  • At least one frontier model provider (OpenAI or Anthropic Claude, etc.)
• Daily ability to use AI coding assistants (e.g., Claude Code, Cursor, GitHub Copilot) for real engineering work
• Knowledge of AI evaluation and safety/guardrails:
  • Offline evals
  • A/B testing of prompts and models
  • Hallucination guardrails, prompt injection defenses, and PII handling
  • Cost and latency management for AI systems
• Solid foundation in architecture and design principles (MVC/DRY/OOP), as well as application architecture

Nice-to-haves

• Experience spanning travel/payments/expense domain or building systems that integrate multiple stakeholders
• Demonstrated ability to improve observability, security, and reliability of AI systems in production