AI Engineer: Agentic Dev & Scalable Backend Architect

TechDigital Group; Hoboken (NJ); On-site; USD 140,000 - 200,000; Full time

Job summary

TechDigital Group is seeking AI Engineers to design agentic development and AI-augmented engineering platforms in Hoboken, NJ. You will build loop engineering workflows, MCP servers, and secure, testable agent-driven systems.

You will collaborate with backend and frontend teams, enforce TDD, and establish CI/CD practices for agent-authored changes while mentoring engineers on safe, scalable designs.

Qualifications

• Hands-on experience with Claude Code or comparable agentic coding tools in production settings.
• Strong understanding of MCP (Model Context Protocol) building and consuming MCP servers.
• Context engineering: managing context windows, prompt caching, and information architecture for long-running agent sessions.
• Awareness of prompt injection and agent-specific security risks.

Responsibilities

• Design and implement loop engineering workflows using Claude Code and similar tools, defining how agents plan, execute, test, and iterate on code changes.
• Architect Model Context Protocol (MCP) servers and tool schemas that are legible and safe for LLM agents to use.
• Define human-in-the-loop checkpoints, autonomy boundaries, and rollback strategies for agent-driven changes.
• Build evaluation harnesses and observability practices to measure agent output quality and catch regressions.
• Design and review microservice and microfrontend architecture using C4 diagrams and Domain-Driven Design principles.
• Drive test-driven development practices across teams, including contract testing between services.
• Own technical decisions across our Java microservices, Node.js services, React/microfrontend UI, and Python tooling.
• Design REST APIs and headless component architectures that support both human developers and AI agents.
• Establish CI/CD practices that safely incorporate agent-authored pull requests.
• Set and enforce security practices for agentic workflows, including prompt injection risk and tool-permission boundaries.
• Mentor senior and staff engineers on effective agent-assisted development.
• Write RFCs and design docs that translate ambiguous problems into actionable technical plans, documents that both humans and agents can act on.

Skills

Claude Code

MCP (Model Context Protocol)

Context engineering

Prompt security awareness

REST API design

Java microservices

ReactJS

Node.js tooling

MongoDB design

Test-driven development

Tools

Java microservices

Node.js

Python

React

MongoDB

REST APIs

Job description

AI Engineers - Agentic Development & AI-Augmented Engineering

Responsibilities

• Design and implement "loop engineering" workflows using Claude Code and similar tools, defining how agents plan, execute, test, and iterate on code changes
• Architect Model Context Protocol (MCP) servers and tool schemas that are legible and safe for LLM agents to use
• Define human-in-the-loop checkpoints, autonomy boundaries, and rollback strategies for agent-driven changes
• Build evaluation harnesses and observability practices to measure agent output quality and catch regressions
• Design and review microservice and microfrontend architecture using C4 diagrams and Domain-Driven Design principles
• Drive test-driven development practices across teams, including contract testing between services
• Own technical decisions across our Java microservices, Node.js services, React/microfrontend UI, and Python tooling
• Design REST APIs and headless component architectures that support both human developers and AI agents
• Establish CI/CD practices that safely incorporate agent-authored pull requests
• Set and enforce security practices for agentic workflows, including prompt injection risk and tool-permission boundaries
• Mentor senior and staff engineers on effective agent-assisted development
• Write RFCs and design docs that translate ambiguous problems into actionable technical plans, documents that both humans and agents can act on

Required Skills & Experience
Agentic Development

• Hands-on experience with Claude Code or comparable agentic coding tools in production settings
• Strong understanding of MCP (Model Context Protocol) building and consuming MCP servers
• Context engineering: managing context windows, prompt caching, and information architecture for long-running agent sessions
• Awareness of prompt injection and agent-specific security risks

Architecture & Backend

• Deep experience with Java microservices
• Strong REST API design skills
• C4 model architecture documentation and system design
• Domain-Driven Design principles
• Node.js and Python for tooling, services, and automation
• MongoDB schema design, performance, and scaling.

Frontend

• ReactJS, headless component architecture, and microfrontend design patterns

Testing & Quality

• Test-driven development (TDD) as a core practice, not an afterthought
• Playwright for end-to-end testing
• Contract testing (e.g., Pact) across microservice boundaries