Skip to main content
Huntington National Bank logo

Lead AI Gateway Engineer

Huntington National Bank

Minnetonka, MNJob$89–93K/yrSeen todayIn the employer's feed · checked in the last 2 days

See where you stand before you apply. No sign-up to start.

You apply on the posting's application page, with no Olive account needed.

Watch jobs like this.

Don't just apply. Show up ready.

Olive works from this exact posting.

At a glance

Compensation
$89–93K/yr
Location
Minnetonka, MN
Work Authorization
Not specified

Olive focuses on jobs in the United States, including remote roles you can work from there.

Job overview

The Lead AI Gateway & Model Infrastructure Engineer designs, builds, and operates Huntington’s enterprise gateway for secure, reliable access to approved AI models. The role focuses on model routing, provider abstraction, security policy enforcement, resiliency, observability, and consumption controls. It partners with AI Platform, Agent Platform, Cloud, Cybersecurity, and application teams, and owns the governed model-access layer rather than model development or agent orchestration.

Skills & qualifications

RequiredNice to have

Skills

Generative AI Model APIs, requiredAPI Gateway Engineering, requiredAPI Proxy Development, requiredAPI Routing, requiredAPI Transformations, requiredAuthentication, requiredAuthorization, requiredQuotas, requiredRate Limiting, requiredThreat Protection, requiredREST APIs, requiredHTTP, requiredJSON, requiredStreaming Interfaces, requiredOAuth 2.0, requiredOpenID Connect, requiredJWT, requiredTLS, requiredCertificates, requiredWorkload Identity, requiredPython, requiredGo, requiredJava, requiredJavaScript, requiredTypeScript, requiredCloud Computing, requiredContainers, requiredKubernetes, requiredTerraform, requiredInfrastructure as Code, requiredGit, requiredCI/CD, requiredAutomated Testing, requiredMonitoring, requiredLogging, requiredDistributed Tracing, requiredHigh Availability, requiredResiliency, requiredDisaster Recovery, requiredPerformance Engineering, required

Qualifications

7+ Years Engineering Experience, requiredApigee or Similar Technologies, nice to haveApigee Configuration Experience, nice to haveShared Platforms in Regulated Environments, nice to have

Benefits

Medical Insurance
401(k) Match
Paid Time Off

Full job description

Description

Position SummaryThe Lead AI Gateway & Model Infrastructure Engineer designs, builds, and operates Huntington’s enterprise gateway for secure and reliable access to approved AI models. This hands-on technical leadership role focuses on model routing, provider abstraction, security policy enforcement, resiliency, observability, and consumption controls.

The engineer partners with AI Platform, Agent Platform, Cloud, Cybersecurity, and application teams. The role owns the governed model-access layer, not model development, AI platform services, or agent orchestration.Core Responsbilities

  • Design, build, and operate enterprise AI Gateway and API Gateway services and supporting infrastructure.

  • Integrate approved models and providers, including Google Vertex AI, Gemini, Anthropic, and internally hosted models.

  • Enable secure access to approved AI models through provider abstraction, model routing, token controls, and policy enforcement.

  • Implement authentication, authorization, OAuth, traffic management, threat protection, rate limits, quotas, and data-protection policies.

  • Configure and manage API proxies, routes, products, policies, shared flows, certificates, and developer access.

  • Integrate REST, event-driven, model, and AI service endpoints across cloud and enterprise environments.

  • Engineer high-availability capabilities, including load balancing, failover, retries, timeouts, health checks, and disaster recovery.

  • Develop reusable gateway policies and engineering patterns for application, model, and AI service integrations.

  • Automate gateway infrastructure, configuration, onboarding, testing, and deployment through Terraform and CI/CD pipelines.

  • Establish monitoring for AI and API traffic, model usage, token consumption, latency, errors, availability, and policy decisions.

  • Troubleshoot complex API and AI Gateway issues and lead root-cause analysis and remediation.

  • Provide technical leadership and partner with Cloud, Cybersecurity, AI Platform, Agent Platform, and application teams.

Required/Basic Skills

  • Minimum 7 years of software, platform, cloud, integration, or API engineering experience.

  • Working knowledge of generative AI model APIs, streaming responses, tokens, context limits, and provider quotas.

  • Strong experience designing and operating API gateways, API management platforms, AI Gateways.

  • Hands-on experience with API proxy development, routing, transformations, authentication, authorization, quotas, rate limiting, and threat protection.

  • Experience with REST APIs, HTTP, JSON, streaming interfaces, OAuth 2.0, OpenID Connect, JWT, TLS, certificates, and workload identity.

  • Software-development experience with Python, Go, Java, JavaScript, or TypeScript.

  • Experience with Google Cloud or another major cloud provider, containers, and Kubernetes.

  • Strong hands-on Terraform experience provisioning cloud infrastructure and managing gateway resources, policies, networking, identities, and environment-specific configurations.

  • Experience implementing infrastructure as code using reusable modules, remote state, automated validation, and controlled promotion across environments.

  • Experience with Git-based development, CI/CD pipelines, automated testing, monitoring, logging, and distributed tracing.

  • Knowledge of high availability, resiliency, disaster recovery, performance engineering, and production incident management.

  • Demonstrated ability to lead complex technical designs and influence multiple engineering teams.

Desired Skills

  • Experience with Apigee, LiteLLM, Google Cloud AI services, Kong AI Gateway, Azure API Management AI Gateway, or similar technologies.

  • Experience managing Apigee configuration

  • Experience with Vertex AI, Gemini, Anthropic, Amazon Bedrock, Azure OpenAI, or self-hosted models.

  • Knowledge of model routing, semantic caching, token accounting, cost controls, and model fallback patterns.

  • Experience with Model Armor, content-safety controls, data-loss prevention, or prompt and response inspection.

  • Familiarity with MCP and A2A protocols and the boundaries between API Gateway, AI Gateway, and Agent Gateway responsibilities.

  • Experience supporting shared technology platforms in a regulated environment.

Exempt Status: (Yes = not eligible for overtime pay) (No = eligible for overtime pay)

Yes

Workplace Type:

Office

Our Approach to Office Workplace Type

Certain positions outside our branch network may be eligible for a flexible work arrangement. We’re combining the best of both worlds: in-office and work from home. Our approach enables our teams to deepen connections, maintain a strong community, and do their best work. Remote roles will also have the opportunity to come together in our offices for moments that matter. Specific work arrangements will be provided by the hiring team.

Compensation Range:

Total Base Pay Range Total Base Pay Range 93,000.00 - 89,000.00 USD Annual

The compensation range represents the anticipated low and high end of the base compensation range for this position. Actual compensation will vary based on various factors including but not limited to location, experience, and education.  Colleagues in this position are also eligible to participate in an applicable incentive compensation plan.  In addition, Huntington provides a variety of benefits to colleagues, including health insurance coverage, wellness program, life and disability insurance, retirement savings plan, paid leave programs, paid holidays and paid time off (PTO).

Huntington is an Equal Opportunity Employer.

Tobacco-Free Hiring Practice: Visit Huntington's Career Web Site for more details.

Note to Agency Recruiters: Huntington will not pay a fee for any placement resulting from the receipt of an unsolicited resume. All unsolicited resumes sent to any Huntington colleagues, directly or indirectly, will be considered Huntington property. Recruiting agencies must have a valid, written and fully executed Master Service Agreement and Statement of Work for consideration.

How this job compares

Set against the 3,602 open Platform Engineer jobs on Olive Jobs, counted November 18, 2026.

Pay
  • This posting$89–93K/yr
  • Minnesota median$99–192K/yr76 salary ranges
  • US median$122–216K/yr3,000 salary ranges

This range's midpoint, $91K, is 40% below the Minnesota median midpoint ($152K) — in the lowest quarter of Platform Engineer salary ranges in Minnesota.

Openings
Olive Jobs lists 84 open Platform Engineer jobs in Minnesota and 3,602 across the US. 11% of them nationwide are listed as remote or flexible.
Hiring the most in Minnesota
Experience
This posting asks for at least 7 years of experience; Platform Engineer postings that state a minimum ask for 5 years at the median (2,980 postings).
Education
711 of the 3,602 open Platform Engineer jobs (20%) ask for a bachelor's degree or higher.

Counted across the open, public US postings on Olive Jobs on November 18, 2026. Figures based on too few postings are left out.

Prepare for this role

You've read the whole posting — now see how you match it.