Lead Engineer, AI Platform

OneMagnify • Detroit, MI

2d

About The Position

OneMagnify is an AI-native, platform-enabled B2B digital agency operating at the intersection of data, technology, and creativity. It helps complex organizations achieve measurable business outcomes by building customer experiences and integrated solutions across digital, media, and technology, using industry expertise, analytics, and artificial intelligence.

The Lead Engineer, AI Platform owns the architecture and evolution of the enterprise AI platform powering AI agents across OneMagnify products and client solutions. The role is at the center of engineering, product, data, and AI delivery, translating emerging AI capabilities into reliable, production-ready systems. The Lead Engineer guides technical direction and execution so teams can deploy secure, measurable, and trusted AI workflows at scale, shaping how the organization builds, governs, and operates AI.

The role establishes the platform foundation that helps product and engineering teams move AI from experimentation into reliable, enterprise-grade production. It supports client-facing applications, AI-powered workflows, and digital platforms where reliability, safety, and performance matter. The role connects agents to enterprise knowledge and establishes evaluation frameworks and governance controls, collaborating with product, engineering, data, security, and delivery teams to build shared capabilities with enterprise scalability and operational discipline.

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 experience.
• 10+ years of software engineering experience, including 3+ years as a technical lead, architect, or similar leadership role supporting production systems.
• Experience building and operating 24x7, multi-region enterprise SaaS platforms on AWS, Google Cloud, or Azure, including infrastructure as code and disaster recovery planning.
• Strong production operations expertise, including observability, metrics, logging, distributed tracing, alerting, service-level objectives, incident response, and postmortem practices.
• Experience designing and operating production AI and LLM-based systems, including agent orchestration, multi-agent architectures, tool integrations, context engineering, and Model Context Protocol (MCP) implementations.
• Expertise with AI platforms such as Amazon Bedrock, Google Vertex AI, Azure AI Foundry, or similar enterprise AI ecosystems.
• Experience building retrieval-augmented generation (RAG) solutions and working with vector databases and knowledge retrieval systems.
• Deep understanding of AI evaluation, testing, governance, and safety practices, including evaluation datasets, LLM-as-judge frameworks, regression testing, and agent containment strategies.
• Hands-on experience incorporating AI-assisted development workflows into CI/CD pipelines, including validation, review, and approval processes.
• Experience integrating enterprise data platforms and designing secure multi-tenant SaaS environments with identity management, role-based access controls, and tenant isolation.
• Fluency in Python, TypeScript, SQL, and Git-based CI/CD practices.
• Proven ability to influence technical direction and collaborate effectively across engineering, product, security, and delivery teams.

Nice To Haves

• Experience building self-service or low-code platforms that enable governed AI agent creation and deployment.
• Familiarity with managed agent runtimes and agent frameworks from major cloud providers.
• Knowledge of security, governance, and AI risk frameworks such as SOC 2, ISO 27001, NIST AI RMF, or ISO/IEC 42001.
• Experience working within agency, consulting, client delivery, or automotive-focused environments.
• Working knowledge of fine-tuning approaches, including supervised fine-tuning, LoRA/PEFT, and preference tuning.
• Experience with additional backend languages such as Java, Go, or C#.
• Experience using AI-enabled engineering workflows, automation, and platform engineering practices to improve development velocity and quality.

Responsibilities

• Own architecture for agent orchestration, multi-agent workflows, tool integrations, and human approval processes across the enterprise AI platform.
• Evaluate models, frameworks, platforms, and vendors, balancing scalability, reliability, quality, and cost.
• Partner with product and engineering leaders to ensure the platform supports current and future AI use cases.
• Design and implement retrieval pipelines and vector-based knowledge systems that connect AI agents to enterprise data and content.
• Determine when prompting, retrieval-augmented generation, or model customization best serves business outcomes.
• Enable product teams to build AI experiences grounded in accurate, relevant enterprise knowledge.
• Create frameworks for evaluating AI performance, including offline and online evaluations, regression testing, red teaming, and release quality gates.
• Design safeguards including least-privilege access, sandboxing, audit trails, approval workflows, and usage controls.
• Define measurable standards for confidently deploying AI solutions to production.
• Lead operation of a multi-region cloud platform, with accountability for availability, performance, disaster recovery, security, and cost management.
• Build observability capabilities, including metrics, tracing, telemetry, alerting, and service-level objectives.
• Lead incident response practices, on-call operations, escalation processes, and continuous improvement through post-incident reviews.
• Mentor and develop AI Platform engineers and establish engineering standards and best practices.
• Collaborate with engineering, product, and delivery teams to accelerate platform adoption and successful implementation.
• Serve as a trusted technical leader for complex architectural decisions and cross-functional trade-offs.

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