Front End AI Engineer
Role details
Job location
Tech stack
Job description
The AI Front End Engineer will build and support a mission-critical agentic AI platform by developing high-performance React/TypeScript interfaces, integrating multi-step LLM workflows, and delivering production-grade front-end features that interact with Java-based backend services. This role ensures reliability, scalability, and seamless user experience across a next-generation AI automation environment. The engineer will design UI components, integrate AI agents, optimize front-end performance, and work closely with AI/ML, backend, and cloud engineering teams to deliver intelligent, low-latency workflows in a fast-paced engineering organization.
Project Details: This position supports a large-scale AI engineering initiative focused on building an enterprise-grade agentic automation platform. The engineer will work on front-end architecture, LLM/agent integrations, real-time data visualization, CI/CD deployments, and cloud-native delivery (GCP preferred). The team is currently expanding its AI agent capabilities and needs someone with strong React/TypeScript depth, Java familiarity, and hands-on experience creating and deploying AI-driven workflows. The engineer will collaborate across AI, platform, and backend teams to ship new features, improve performance, and ensure stable, secure, and scalable front-end experiences.
Due to client requirements this role is only open to USC or GC candidates
Requirements
Do you have experience in UI implementation?, * Hands-on AI agent development - experience building agentic workflows using LangChain, LangGraph, MCP, or similar orchestration frameworks
- 5+ years AI/ML engineering - production-grade LLM, RAG, or ML system development
- Strong React + TypeScript engineering - modern component patterns, state management, real-time UI, and performance optimization
- Java experience - enterprise or production use (Java 18 preferred)
- CI/CD pipeline experience - GitHub Actions, Jenkins, or equivalent for deploying front-end and full-stack features
- Cloud engineering experience - GCP preferred; AWS or Azure acceptable
- LLM integration experience - connecting front-end workflows to LLM reasoning, retrieval, and agent outputs
- RAG pipeline familiarity - grounding LLM responses with vector stores, embeddings, and retrieval flows
- Real-time data visualization - WebSockets, charts, dashboards, or interactive telemetry views
- Agile engineering collaboration - working with AI/ML, backend, and platform teams to ship features quickly
Due to client requirements this role is only open to USC or GC candidates
Desired Skills
- Experience with multi-agent architectures - designing agent collaboration patterns, state machines, and tool-calling flows
- Advanced RAG pipeline design - embeddings, re-ranking, vector DB tuning, and grounding strategies
- Strong UI/UX intuition - building intuitive workflows, dashboards, and interactive AI-driven interfaces
- Real-time visualization frameworks - Plotly, Recharts, D3.js, or similar charting libraries
- Backend integration experience - connecting React front-ends to Java APIs, microservices, and event-driven systems
- Performance tuning for LLM-powered UIs - caching, streaming responses, and optimizing latency
- Containerization and cloud-native delivery - Docker, Kubernetes, and cloud deployment patterns
- Monitoring and observability familiarity - OpenTelemetry, Prometheus, Grafana, or similar tooling
- Security best practices - JWT/OAuth, secure API integration, and front-end hardening
- Experience with modern state management - Redux Toolkit, Zustand, or equivalent
- Comfort working in fast-moving AI product teams - rapid iteration, experimentation, and cross-functional collaboration
Benefits & conditions
3.43.4 out of 5 stars Atlanta, GA Remote $90 - $100 an hour - Contract