Sr. Full Stack Engineer - AI Forward

Salary: $128,000 - 168,000 per year Requirements: 5+ years of full-stack web application development experience with Node.js, JavaScript, TypeScript, and modern frameworks. Extensive experience building scalable applications and microservices with React, Next.js, Node.js, Express, HTML, and CSS, including hands-on TypeScript work across frontend and backend systems. Strong knowledge of RESTful API design, OpenAPI specifications, API integration, and modern data-fetching patterns. Extensive experience with MySQL, MongoDB, PostgreSQL, and Redis, including data modeling trade-offs. Experience with performant React applications, hooks, and state management such as Redux; familiarity with micro-frontends and module federation. Experience with Docker, containerized environments, CDNs, caching, performance optimization, and security considerations. Knowledge of JavaScript build tools such as Webpack or Vite, and proficiency with Chrome DevTools and frontend performance profiling. Experience with SPA, PWA, responsive design, and MPA architectures; a strong foundation in data structures, algorithms, database design, software architecture, design patterns, and engineering best practices. At least 1 year of hands-on experience integrating LLM APIs, such as OpenAI or Anthropic, into production or near-production systems. Demonstrated ability to build or extend AI agents that use tool calling, function execution, and structured output; experience shipping at least one agent that performs multi-step autonomous tasks. Solid understanding of agentic patterns, including ReAct loops, planning and task decomposition, tool orchestration, memory architectures, self-correction, human-in-the-loop checkpoints, graceful fallbacks, and multi-agent coordination. Familiarity with agent frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or Claude Agent SDK, or experience with custom orchestration loops; ability to design tool schemas, manage agent state, and troubleshoot nondeterministic behavior. Experience designing or contributing to MCP servers or similar context-orchestration layers. Ability to manage token budgets through prompt optimization, caching, and cost monitoring. Comfortable using AI coding assistants such as GitHub Copilot, Claude Code, Claude Cowork, or Cursor in daily development, and writing effective prompts for code generation, refactoring, testing, and documentation. Understanding of foundational LLM concepts, including tokens, temperature, context windows, embeddings, and RAG; ability to assess AI-generated code for correctness, security, and performance. Nice to have: experience with AWS, Azure, or GCP; ecommerce or retail purchase journeys; legacy application modernization; vector databases and RAG pipelines; model fine-tuning or distillation; GraphQL; or contributions to open-source AI tooling or the MCP ecosystem. Responsibilities: Design, develop, and own full-stack product features across React/Next.js frontends and Node.js/Express microservices. Build AI-powered experiences such as intelligent search, personalized recommendations, automated content generation, and conversational commerce. Develop agentic systems that plan, reason through multi-step tasks, select and call tools, handle errors, and escalate to people when confidence is low. Implement agent patterns such as ReAct loops, planning, reflection, memory, and multi-agent coordination. Develop and maintain MCP servers that make ecommerce tools and data—such as catalog, pricing, inventory, and orders—available to LLM-powered clients. Integrate LLM APIs into production workflows with appropriate error handling, fallback strategies, and cost controls. Create and maintain prompts, evaluation harnesses, and monitoring for AI features, managing them as versioned, reviewable code. Optimize frontend performance, including Core Web Vitals, page load time, and time to first byte. Design clean, well-documented, backward-compatible APIs. Build shared developer tools, including CLI utilities, code generators, reusable component libraries, and AI-powered internal tools. Improve CI/CD pipelines, containerized builds, and deployment workflows. Contribute to architecture decisions, code reviews, and technical design documents. Work with product and design stakeholders to turn business needs into technical designs. Mentor engineers on AI integration patterns, prompt engineering, and modern full-stack practices. Keep up with AI/ML tools, LLM developments, and the MCP ecosystem, and share relevant learnings with the team. Technologies: AI AI Agents API AWS Azure Backend CI/CD Claude Code Copilot CSS Cursor Docker Fine-tuning Frontend GCP GitHub GraphQL JavaScript LLM MCP MongoDB MySQL Network OpenAPI PWA PostgreSQL RAG React Redis Redux Security TypeScript Webpack Web Windows microservices NodeJS Cloud Flow Support REST Fullstack More: We are CarParts.com, an ecommerce platform for auto care and maintenance. We offer drivers quality parts at competitive prices and let them schedule appointments with trusted mechanics through our website. Our digital experience is supported by a national, company-owned distribution network. With more than 1,000 employees worldwide, we are growing following a strategic partnership and $35 million investment. We are a fast-paced, performance- and data-focused team that values safety, customer focus, excellence, accountability, collaboration, and internal growth. We are investing in AI-powered engineering, including intelligent agents, LLM integrations, and MCP servers. This full-time role is based at our Long Beach, California headquarters and is fully in-office; remote and hybrid arrangements are not available. We are an equal-opportunity employer. last updated 42 week of 2026