Senior Engineer, AI Platform

OneMagnify • Detroit, MI

4d

About The Position

OneMagnify is an AI-native, platform-enabled B2B digital agency working across data, technology, and creativity. As a Senior Engineer, AI Platform, you will help build the foundation for AI across the company’s products, delivery teams, and client programs. Working with the AI Platform team, you will create systems that enable AI agents to operate reliably, securely, and at scale in business environments.

The role combines software engineering, AI platforms, and cloud infrastructure. You will shape how teams develop, deploy, and evolve AI-powered solutions, supporting applications across customer experience, marketing technology, data, and digital solutions. You will work with engineering, product, analytics, and client-facing delivery teams to turn emerging AI capabilities into production-ready solutions with measurable business outcomes.

The platform will include agent workflows, retrieval systems, evaluation frameworks, and guardrails designed to support consistent business value, reliability, and enterprise governance. The position also contributes to cloud operations, platform reliability, engineering standards, and organization-wide adoption of AI capabilities.

Requirements

• Experience in integrated marketing, digital agency, marketing services, or consulting environments.
• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
• At least 5 years of professional software engineering experience.
• Experience building and operating production services on AWS, Google Cloud, or Azure, including containers, serverless technologies, managed databases, and infrastructure as code.
• Experience with production operations, including observability, monitoring, logging, tracing, alerting, incident response, and on-call support.
• Hands-on experience building LLM-powered applications or AI agents, including orchestration, tool integrations, context engineering, and the Model Context Protocol (MCP).
• Experience with Amazon Bedrock, Google Vertex AI, Azure AI Foundry, or comparable AI platforms.
• Experience with retrieval-augmented generation (RAG), embeddings, vector databases or vector search, and GraphQL or REST APIs.
• Experience building automated evaluation frameworks, testing LLM outputs, and implementing AI-system guardrails.
• Experience integrating AI coding agents into engineering workflows and CI/CD pipelines.
• Strong proficiency in Python, TypeScript, SQL, and Git-based development practices.
• Ability to collaborate effectively across product, engineering, analytics, and delivery teams.

Nice To Haves

• Experience extending AI-assisted software delivery into coordinated coding, testing, and review workflows.
• Experience building self-service or governed platforms that enable non-technical users to create and deploy AI agents.
• Experience with graph databases and knowledge graph architectures.
• Experience operating 24x7, multi-region SaaS platforms and disaster recovery environments.
• Familiarity with managed agent runtimes from major cloud providers.
• Working knowledge of fine-tuning approaches such as supervised fine-tuning, LoRA/PEFT, or preference tuning.
• Experience with Java, Go, or C#.
• Experience supporting enterprise client programs in marketing, technology, data, or customer experience domains.

Responsibilities

• Develop tooling that enables AI agents to participate in coding, testing, and code review workflows with appropriate human oversight.
• Integrate AI-assisted development capabilities into CI/CD pipelines and engineering practices.
• Use practical AI applications to improve software quality, delivery speed, and developer productivity.
• Build agent orchestration capabilities, including multi-agent workflows, tool integrations, MCP servers, and approval checkpoints.
• Develop retrieval pipelines, APIs, and data services that connect AI agents to enterprise knowledge sources.
• Partner with product and engineering teams to apply platform capabilities to business and client use cases.
• Implement guardrails to keep agent actions secure, auditable, and aligned with business requirements.
• Build evaluation frameworks and automated testing approaches for prompts, models, and agent workflows.
• Establish quality controls that support moving AI-powered solutions into production.
• Build and maintain cloud infrastructure, deployment pipelines, and platform services using infrastructure-as-code practices.
• Improve platform reliability through observability, monitoring, tracing, and alerting.
• Participate in on-call rotations, incident response, and continuous platform improvements.
• Participate in architecture discussions, design reviews, and the development of engineering standards.
• Collaborate with engineering, product, and delivery teams to support platform adoption across the organization.
• Share knowledge and help establish best practices for building and operating AI-powered systems.

Benefits

• Medical coverage
• Dental coverage
• Vision coverage
• 401(k) retirement plan
• Paid holidays
• Flexible Time Off (FTO)
• Additional programs focused on wellness, financial security, and professional growth

What This Job Offers

• Job Type: Full-time
• Career Level: Senior