Senior AI Engineer

Stellent IT LLC; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

Stellent IT LLC is seeking a Senior AI Engineer to lead development of AI platforms, developer tools, and agentic capabilities. The role requires delivering end-to-end technical work, collaborating with engineers and leaders, and establishing reusable patterns for custom agents and MCP services.

The ideal candidate has strong experience with AI/LLM integration, cloud-based services, secure APIs, and scalable architectures, with a track record of delivering production-grade solutions.

Qualifications

• 5-7 years of experience in software engineering, platform engineering, AI engineering, or a related technical discipline.
• Proven experience delivering high-quality software solutions in production environments.
• Hands-on experience building or integrating AI, LLM, developer-platform, or automation capabilities.
• Experience with cloud-based AI services platform such as GCP, Gemini, and Vertex AI or comparable model platforms.
• Solid understanding of application architecture, integration patterns, APIs, and software design principles.
• Experience developing Java REST APIs and services with Spring Boot and working knowledge of React.js or comparable front-end technologies.
• Experience with secure API integrations and OAuth 2.0 / OpenID Connect authorization patterns, including service accounts, client credentials, or delegated user access.
• Understanding of the software development lifecycle, CI/CD, observability, reliability, security, privacy, and responsible AI practices.
• Strong problem-solving skills, attention to detail, technical communication, and ability to collaborate effectively across teams.

Responsibilities

• Develop and maintain AI platforms, tools, and frameworks used by engineers across the company.
• Implement AI platform services, orchestration patterns, reference implementations, and shared integration components.
• Design and deliver tools that support development of custom agents and workflows.
• Integrate and operationalize AI tools and services with cloud, security, development, and enterprise technology platforms.
• Build secure, scalable, reliable, observable, performant, and maintainable services for custom agents and AI tool integrations.
• Provide technical support and guidance to development teams building, deploying, and operating custom agents and MCP servers.
• Contribute to framework lifecycle practices, including versioning, release management, documentation, adoption, support, and continuous improvement.
• Implement logging, metrics, token-utilization monitoring, tracing, and other operational capabilities for AI services running on GCP.
• Apply enterprise security, privacy, responsible AI, access-control, governance, cost-management, and model-risk practices to AI solutions.
• Collaborate with development teams, security, and architecture to define requirements and deliver platform capabilities.
• Participate in code reviews, technical discussions, troubleshooting, and knowledge-sharing activities.
• Mentor junior engineers on the team as well as engineers on our development teams contributing to a culture of continuous improvement.

Skills

AI engineering

Cloud platforms

Java REST APIs

Security & privacy

Collaboration

Education

Bachelor's degree or equivalent

Tools

Claude Code

GitHub Copilot

MCP servers

Spring Boot

React.js

Job description

Job Tite: Senior AI Engineer

Location: Remote

Duration: Nov 2, 2026 Feb 9, 2027

JOB DESCRIPTION

Job Summary

A senior role focused on developing and supporting AI platforms, developer tools, and agentic application capabilities. This position requires significant experience delivering high-quality software solutions, applying sound application and integration patterns, and contributing to the design of secure and scalable AI capabilities. The Senior AI Engineer will own significant technical work efforts end-to-end, collaborate with development teams and technical leaders, and help establish reusable patterns for building and operating custom agents throughout the company.

Responsibilities

• Develop and maintain AI platforms, tools, and frameworks used by engineers across the company, including Claude Code, GitHub Copilot, MCP servers, plugins, skills, and agentic frameworks.
• Implement AI platform services, orchestration patterns, reference implementations, and shared integration components in collaboration with technical leads and architects.
• Design and deliver tools that support development of custom agents and workflows, including sequential, multi-agent, and deterministic graph-based solutions.
• Integrate and operationalize AI tools and services with cloud, security, development, and enterprise technology platforms.
• Build secure, scalable, reliable, observable, performant, and maintainable services for custom agents and AI tool integrations.
• Provide technical support and guidance to development teams building, deploying, and operating custom agents and MCP servers.
• Contribute to framework lifecycle practices, including versioning, release management, documentation, adoption, support, and continuous improvement.
• Implement logging, metrics, token-utilization monitoring, tracing, and other operational capabilities for AI services running on GCP.
• Apply enterprise security, privacy, responsible AI, access-control, governance, cost-management, and model-risk practices to AI solutions.
• Collaborate with development teams, security, and architecture to define requirements and deliver platform capabilities.
• Participate in code reviews, technical discussions, troubleshooting, and knowledge-sharing activities.
• Mentor junior engineers on the team as well as engineers on our development teams contributing to a culture of continuous improvement.

Education

Bachelor's degree or equivalent work experience in computer science, engineering, artificial intelligence, or a related field

Basic Qualifications

• 5-7 years of experience in software engineering, platform engineering, AI engineering, or a related technical discipline
• Proven experience delivering high-quality software solutions in production environments
• Hands-on experience building or integrating AI, LLM, developer-platform, or automation capabilities
• Experience with cloud-based AI services platform such as GCP, Gemini, and Vertex AI or comparable model platforms
• Solid understanding of application architecture, integration patterns, APIs, and software design principles
• Experience developing Java REST APIs and services with Spring Boot and working knowledge of React.js or comparable front-end technologies
• Experience with secure API integrations and OAuth 2.0 / OpenID Connect authorization patterns, including service accounts, client credentials, or delegated user access
• Understanding of the software development lifecycle, CI/CD, observability, reliability, security, privacy, and responsible AI practices
• Strong problem-solving skills, attention to detail, technical communication, and ability to collaborate effectively across teams

Preferred Qualifications

• Hands-on experience using Claude Code and GitHub Copilot in an engineering workflow, including custom instructions, prompts, skills, plugins, or extensions
• Designing or implementing custom AI agents, reusable orchestration patterns, shared integrations, or reference implementations
• Building sequential, multi-agent, or deterministic graph-based agent workflows
• Building or integrating MCP servers and clients to expose tools, resources, or data sources to AI agents
• Enabling agent-to-agent communication using A2A or comparable protocols
• Experience with Google ADK, Spring AI, LangChain, LangChain4j, or similar LLM integration libraries and SDKs
• Experience with Gemini Agent Platform / Vertex AI capabilities such as model garden, model runtime, model gateway, or agent gateway
• Implementing model governance controls such as GCP Model Armor, cost controls, token limits, rate limits, and access policies
• Implementing logging, metrics, distributed tracing, token-utilization monitoring, and operational dashboards for AI services on GCP
• Exposure to containerization, microservices, and cloud-native application architecture
• Experience working with CI/CD pipelines in Harness and Azure DevOps, including automated build, test, security, and release workflows
• Familiarity with Agile/Scrum methodologies and development practices for shared platform capabilities

Technical Skills Required

• AI Platforms: GCP, Gemini, Vertex AI, model garden, model runtime, model gateway, and agent gateway
• AI Engineering: custom agent design, sequential workflows, multi-agent systems, deterministic graph-based agents, and reusable orchestration patterns
• Developer Tools: Claude Code, GitHub Copilot, custom instructions, prompts, skills, plugins, and extensions
• Agent Integration: MCP servers and clients, tools, resources, data-source integrations, A2A patterns, and agent-to-agent communication
• Frameworks: Google ADK, Spring AI, LangChain, LangChain4j, or comparable AI/LLM integration libraries
• Application Development: Java, Spring Boot, REST APIs, React.js, microservices, and cloud-native application patterns
• Security and Governance: OAuth 2.0, OpenID Connect, service accounts, delegated access, model governance, GCP Model Armor, privacy, responsible AI, and access control
• Operations: CI/CD, Harness, Azure DevOps, logging, metrics, tracing, token utilization, performance, reliability, and incident support

Strengths and Capabilities

• Technical Expertise: Strong, hands-on knowledge of AI/LLM integration, agent development, platform engineering, and enterprise software delivery.
• Platform Proficiency: Ability to build, integrate, operate, and support AI platforms and developer toolkits using GCP, Gemini, Vertex AI, Claude Code, GitHub Copilot, MCP, and related technologies.
• Application and Integration Design: Ability to apply sound design patterns and contribute to reusable orchestration patterns, shared integration components, and maintainable frameworks for custom agents and MCP services.
• Technical Delivery: Ability to own substantial work efforts end-to-end, make sound technical decisions, deliver high-quality solutions, and resolve complex implementation and integration issues.
• Security and Responsible AI: Ability to apply secure-by-design, privacy, governance, access-control, cost-management, and responsible AI principles to enterprise AI solutions.
• Product Awareness: Ability to understand developer and business needs, provide useful feedback on platform capabilities, and contribute to continuous improvement.
• Collaboration and Communication: Ability to work effectively with development teams, technical leads, product management, security, architecture, lines of business, and other stakeholders.
• Mentorship and Advocacy: Ability to share knowledge, support junior engineers, and encourage effective adoption of AI tools, platforms, frameworks, and best practices.
• Adaptability: Ability to learn and apply rapidly evolving AI technologies, developer tools, platform capabilities, and industry practices.