JOB DESCRIPTION

Full Stack Engineer	— Agentic AI
Department:	Engineering / AI
Location:	Hybrid / Remote
Experience:	5+ Years

Products

React / Next.js, Node.js / Python, Agentic Workflows, Cloud & DevOps, API Design

ABOUT THE ROLE

We are seeking a Full Stack Engineer with 5+ years of experience to design and deliver end-to-end AI-powered applications, with a specific focus on deploying and operationalizing Agentic Workflows in production. You will bridge the gap between front-end user experiences and backend AI systems — building the interfaces, APIs, data pipelines, and orchestration layers that bring autonomous AI agents to life for enterprise users.

KEY RESPONSIBILITIES

Frontend Development

• Design, build, and deploy full-stack web applications that expose agentic AI capabilities to end users via intuitive interfaces.
• Develop responsive, accessible UIs using React, Next.js, or Vue.js that visualize agent reasoning steps, tool usage, and streaming outputs.
• Implement real-time UI patterns (WebSockets, Server-Sent Events) to surface live agent progress and intermediate results to users.
• Build agent configuration and prompt management consoles for business users to interact with and tune agentic systems.
• Design component libraries and design systems that support multi-agent interaction patterns, chat interfaces, and workflow dashboards.

Backend & Agentic Workflow Engineering

• Build and deploy agentic workflow orchestration layers using LangGraph, AutoGen, CrewAI, or custom orchestration frameworks.
• Design and implement RESTful and GraphQL APIs that expose agent capabilities to front-end applications and third-party integrations.
• Develop backend services in Node.js and/or Python to manage agent state, session memory, and tool-call execution pipelines.
• Implement human-in-the-loop (HITL) approval workflows, escalation triggers, and audit trails within agentic pipelines.
• Build and manage MCP (Model Context Protocol) server integrations to expose databases, APIs, and enterprise data as agent tools.
• Integrate vector databases (Pinecone, Weaviate, pgvector) and knowledge graph layers to support RAG - grounded agent responses.

Deployment & DevOps

• Deploy agentic systems on cloud platforms (AWS / GCP / Azure) using containerized services (Docker, Kubernetes, ECS/GKE).
• Build CI/CD pipelines for full-stack applications and agent workflows with automated testing, staging gates, and rollback support.
• Implement observability stacks (logging, tracing, metrics) for both frontend interactions and backend agent execution chains.
• Manage infrastructure as code (Terraform, Pulumi) for repeatable, auditable agentic system deployments.

Security, Governance & Quality

• Apply security best practices for AI-powered applications: API authentication, rate limiting, prompt injection defense, and output validation.
• Implement role-based access control (RBAC) and audit logging for agentic workflows in regulated or enterprise environments.
• Write comprehensive unit, integration, and end-to-end tests for both UI components and agentic backend services.

REQUIRED SKILLS & EXPERIENCE

• 5+ years of full-stack engineering experience delivering production applications.
• Proven experience deploying at least one agentic AI workflow or LLM-powered application to production.
• Strong proficiency in React or Next.js (frontend) and Node.js and/or Python (backend).
• Experience with RESTful API design, GraphQL, and microservices architecture.
• Familiarity with at least one agent orchestration framework: LangChain/LangGraph, AutoGen, CrewAI, or Semantic Kernel.
• Hands-on experience with SQL and NoSQL databases; understanding of vector database concepts for RAG pipelines.
• Solid understanding of streaming data patterns for real-time AI output rendering (SSE, WebSockets).
• Experience with containerization (Docker) and deployment on major cloud platforms (AWS / GCP / Azure).
• Proficiency with Git-based workflows, code reviews, and trunk-based development practices.
• Strong communication skills to collaborate across data science, AI engineering, product, and business stakeholder teams.

NICE TO HAVE

• Experience with Kubernetes, Helm, or GitOps-based deployment patterns for scalable agent infrastructure.
• Familiarity with MCP (Model Context Protocol) server design and tool-use integration patterns.
• Exposure to LLM evaluation frameworks (RAGAS, Promptfoo, or LLM-as-judge) and agent testing strategies.
• Experience with data lineage, metadata management, or enterprise data catalog platforms.
• Knowledge of fine-tuning workflows and model serving (vLLM, TGI, Ollama) for self-hosted LLMs.
• Contributions to open-source AI tooling or developer experience projects.

WHAT WE OFFER

• Opportunity to work at the frontier of applied Agentic AI — building real enterprise products, not prototypes.
• Cross-functional teams combining AI researchers, data engineers, and product designers.
• Competitive salary, flexible working arrangements, and access to top-tier AI tooling and infrastructure.
• Continuous learning culture with investment in training, certifications, and conference participation.

End of Job Description