Principal AI Engineer

Heitmeyer Consulting; Columbus (OH); On-site; USD 180,000 - 230,000; Full time

Job summary

Heitmeyer Consulting seeks a Principal AI Engineer to lead the design, development, and operations of enterprise AI platforms and developer tools. This hands-on role drives reusable AI capabilities across the organization, guiding engineering teams and ensuring scalable, secure solutions.

You will architect AI services, integrate with cloud and security platforms, and mentor engineers while delivering production-ready implementations using Java/Spring Boot and modern AI tooling.

Qualifications

• 7–10 years of experience in software engineering, platform engineering, AI engineering, or a related technical discipline.
• Proven experience designing and delivering production-quality AI, LLM, or developer-platform solutions.
• Hands-on experience with GCP and AI services such as Gemini and Vertex AI, or comparable platforms.
• Strong understanding of AI agent architecture, LLM integrations, orchestration patterns, and reusable platform capabilities.
• Strong Java and Spring Boot development experience.
• Experience developing and integrating REST APIs and OAuth 2.0 / OpenID Connect security patterns.
• Experience with software development lifecycle, CI/CD, observability, security, reliability, and cloud-native development.

Responsibilities

• Lead the architecture and development of enterprise AI platforms, agent frameworks, and developer productivity capabilities.
• Design and build reusable AI services, orchestration patterns, reference implementations, and shared integrations.
• Develop and integrate AI solutions using GCP, Gemini, Vertex AI, Claude Code, GitHub Copilot, MCP, and agentic frameworks.
• Build secure, scalable, observable, and maintainable custom-agent capabilities for enterprise engineering teams.
• Integrate AI services with cloud, security, identity, and enterprise technology platforms.
• Develop secure REST APIs and integrations using Java, Spring Boot, OAuth 2.0, and OpenID Connect.
• Establish standards for AI platform versioning, releases, documentation, support, adoption, and continuous improvement.
• Implement observability for AI services, including logging, metrics, tracing, token utilization, performance, and operational health.
• Apply responsible AI, privacy, access control, governance, model-risk, and cost-management practices.
• Provide hands-on technical guidance, training, and support to engineering teams adopting shared AI capabilities.
• Partner with product management, security, architecture, and business teams to define the AI platform roadmap.
• Mentor engineers and provide technical leadership throughout the development and delivery lifecycle.

Skills

Technical leadership

Architecture design

Mentoring

Hands-on

Agile/Scrum

Problem solving

Tools

GCP

Gemini

Vertex AI

Claude Code

GitHub Copilot

MCP

Agent frameworks

Java

Spring Boot

REST APIs

OAuth 2.0

OpenID Connect

CI/CD

Observability

Security

Job description

Job Description

We are seeking a Principal AI Engineer to join the Engineering Frameworks team and lead the design, development, integration, and operational support of enterprise AI platforms and developer tools.

This is a highly hands-on technical leadership role focused on building reusable AI capabilities that enable engineering teams across the organization to develop and deploy solutions for their lines of business. The ideal candidate will have direct, production-level experience with GCP, Gemini, Vertex AI, Claude Code, GitHub Copilot, MCP, and agentic application frameworks, along with strong Java/Spring Boot development experience.

The role will help establish scalable AI engineering patterns, shared services, integrations, and governance practices while providing technical leadership and guidance to engineering teams.

Key Responsibilities

• Lead the architecture and development of enterprise AI platforms, agent frameworks, and developer productivity capabilities.
• Design and build reusable AI services, orchestration patterns, reference implementations, and shared integrations.
• Develop and integrate AI solutions using GCP, Gemini, Vertex AI, Claude Code, GitHub Copilot, MCP, and agentic frameworks.
• Build secure, scalable, observable, and maintainable custom-agent capabilities for enterprise engineering teams.
• Integrate AI services with cloud, security, identity, and enterprise technology platforms.
• Develop secure REST APIs and integrations using Java, Spring Boot, OAuth 2.0, and OpenID Connect.
• Establish standards for AI platform versioning, releases, documentation, support, adoption, and continuous improvement.
• Implement observability for AI services, including logging, metrics, tracing, token utilization, performance, and operational health.
• Apply responsible AI, privacy, access control, governance, model-risk, and cost-management practices.
• Provide hands-on technical guidance, training, and support to engineering teams adopting shared AI capabilities.
• Partner with product management, security, architecture, and business teams to define the AI platform roadmap.
• Mentor engineers and provide technical leadership throughout the development and delivery lifecycle.

Required Qualifications

• 7–10 years of experience in software engineering, platform engineering, AI engineering, or a related technical discipline.
• Proven experience designing and delivering production-quality AI, LLM, or developer-platform solutions.
• Hands‑on experience with GCP and AI services such as Gemini and Vertex AI, or comparable platforms.
• Strong understanding of AI agent architecture, LLM integrations, orchestration patterns, and reusable platform capabilities.
• Strong Java and Spring Boot development experience.
• Experience developing and integrating REST APIs and OAuth 2.0 / OpenID Connect security patterns.
• Experience with software development lifecycle, CI/CD, observability, security, reliability, and cloud‑native development.
• Ability to provide technical leadership while remaining hands‑on with architecture and development.

Preferred Qualifications

• Hands‑on experience with Claude Code and GitHub Copilot, including custom instructions, prompts, skills, plugins, or extensions.
• Experience building or integrating MCP servers and clients.
• Experience with A2A or comparable agent‑to‑agent communication protocols.
• Experience with Google ADK, Spring AI, LangChain, LangChain4j, or similar AI/LLM frameworks.
• Experience with Gemini Agent Platform / Vertex AI capabilities, including model gateways or agent gateways.
• Experience implementing AI governance, model controls, token limits, rate limits, access policies, and cost controls.
• Experience with AI observability, including distributed tracing, token utilization, operational dashboards, and performance monitoring.
• Experience with containers, microservices, and cloud‑native architecture.
• Experience with Harness and Azure DevOps CI/CD pipelines.
• Experience working in Agile/Scrum environments and supporting shared platform products.

Technical Skills

• GCP, Gemini, Vertex AI
• AI/LLM and Agent Architecture
• Claude Code and GitHub Copilot
• MCP Servers and Clients
• A2A / Agent‑to‑Agent Integrations
• Google ADK, Spring AI, LangChain, or LangChain4j
• Java and Spring Boot
• REST APIs
• React.js
• OAuth 2.0 / OpenID Connect
• Microservices and Cloud‑Native Architecture
• CI/CD, Harness, Azure DevOps
• AI Observability and Monitoring
• Security, Governance, Privacy, and Responsible AI

Ideal Candidate

The ideal candidate is a senior, hands‑on AI engineer who can operate at both the architecture and implementation levels. They should have demonstrated experience building enterprise AI capabilities—not simply experimenting with AI tools—and be able to establish reusable patterns that other engineering teams can adopt.

This person should be comfortable leading technical initiatives, solving complex integration and architecture problems, working across security and engineering teams, and mentoring others while remaining directly involved in development.