Fullstack Software Engineer, Gen AI Systems

Remote Hiring Remotely in USA Mid level Remote Hiring Remotely in USA Mid level Build and own production AI-powered products across the frontend, backend, data, and cloud stack. Design multi-agent systems and RAG pipelines, orchestrate AI workflows, and deploy reliable, scalable features. Responsibilities include model serving, latency and cost optimization, prompt engineering, model evaluation, cloud infrastructure, and end-to-end product development using React, Node.js, PostgreSQL, and major cloud platforms. The summary above was generated by AI

This is a remote position.

We are hiring a Fullstack Software Engineer with deep experience building AI-powered products in production. This is a high-ownership role at the intersection of fullstack engineering, AI systems design, and product thinking. You will not simply integrate APIs. You will architect multi-agent systems, design RAG pipelines, and take AI features from concept to production with full accountability for system reliability, performance, and cost.

You will work across the entire stack (frontend, backend, data, and cloud infrastructure) and operate as a product-minded engineer who drives outcomes, not just ships code. You will collaborate directly with Product Owners, Subject Matter Experts, and cross-functional teams to translate ambiguous requirements into production-ready solutions.

If you thrive in ambiguity, care deeply about outcomes over output, and want to shape how AI is built into real products, this role is for you., * Own features end-to-end: from UI (React/Next.js) through API design (Node.js/NestJS) to cloud deployment.

• Partner with Product Owners and Subject Matter Experts to translate requirements into shipped solutions.
• Contribute product ideas that improve usability, performance, and business impact.

AI Engineering and Systems Design

• Design and build multi-agentic systems where autonomous AI agents collaborate to solve complex, real-world task
• Architect and implement RAG pipelines using vector databases and LLM orchestration frameworks.
• Take AI-powered features from prototype to production, owning model serving, latency optimization, cost management, and system reliability.
• Work with AI SDK, LangGraph/LangChain, CrewAI, or equivalent tools to build and orchestrate AI workflows.

Cloud Infrastructure and Deployment

• Design, deploy, and manage scalable systems on cloud platforms (AWS, GCP, or Azure).
• Apply cloud-agnostic thinking: understand core concepts regardless of provider.

• 3-5+ years of professional experience building production applications with React/Next.js, Node.js/NestJS, and PostgreSQL.
• Hands-on experience with at least one of: AI SDK (Vercel), LangGraph/LangChain, or CrewAI.
• Proven track record designing, orchestrating, and deploying multi-agent AI systems in production.
• Working experience with vector databases (Pinecone, Weaviate, pgvector, or similar) and RAG pipeline design.
• Strong understanding of AI deployment and system design: model serving, latency optimization, cost management, and production reliability.
• Experience with prompt engineering, model selection, and evaluation.
• Solid understanding of cloud concepts and services across AWS, GCP, or Azure.
• Experience deploying and managing production workloads in at least one major cloud platform.