Quick Overview
Salary
$70/hr
Seniority
Mid Senior
Work mode
Remote
Location
United States
Posted
21 hours ago
DockerAPI GatewayAWSELKLoad BalancingSplunkAzureGitHub ActionsGoogle CloudGrafanaGraphQLHelmJWTJenkinsKubernetesLLMPrometheusREST
Job Description
Role: Platform Engineer (Kong gateway)
Location: 100% Remote
Duration: 6 Months Contract with possible Extension
Location: 100% Remote
Duration: 6 Months Contract with possible Extension
Rate: $70/hour W2
Client: Allstate
VISA: USCs preferred
Job Description:
Looking for a skilled Kong Administrator / AI Gateway Engineer with experience in API Gateway management, Kong administration, and knowledge on AI/LLM proxy development
Looking for a skilled Kong Administrator / AI Gateway Engineer with experience in API Gateway management, Kong administration, and knowledge on AI/LLM proxy development
Required Experience:
7-12 years of experience in API Management, Middleware, or Platform Engineering.
Minimum 3 to 5 years of hands-on experience with Kong Gateway Administration.
7-12 years of experience in API Management, Middleware, or Platform Engineering.
Minimum 3 to 5 years of hands-on experience with Kong Gateway Administration.
Skills:
Kong Gateway (OSS/Enterprise), Kong Konnect
API Management & API Lifecycle Management
AI Gateway / LLM Proxy Development
OpenAI / Azure OpenAI Integration
REST APIs, GraphQL
OAuth2, JWT, OIDC, API Security
Kubernetes, Docker, Helm
CI/CD (Jenkins, GitHub Actions, Azure DevOps)
Monitoring: Prometheus, Grafana, ELK/Splunk
Cloud Platforms: Azure, AWS, or Google Cloud Platform
Kong AI Gateway Configuration & Administration
LLM Traffic Routing, Load Balancing and Failover Management
Prompt Management, Prompt Security and Guardrails
AI Security, Responsible AI and Model Governance
Token Usage Monitoring, Rate Limiting and Cost Optimization
Multi-LLM Integration (OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini, Mistral, Llama)
Retrieval-Augmented Generation (RAG) Architecture Concepts
Vector Databases:
LLMOps, AI Observability and Model Performance Monitoring
AI API Governance, Compliance and Data Protection
Prompt Caching, Semantic Caching and Response Optimization
Model Gateway Policy Development and AI Consumption Controls
MCP (Model Context Protocol) and AI Agent Integration Concepts
GenAI Platform Engineering and Enterprise AI Enablement
Key Responsibilities:
Design and implement enterprise-grade AI Gateway solutions using Kong AI Gateway.
Configure AI-specific policies including prompt logging, content filtering, token controls, and guardrails.
Enable secure access to multiple LLM providers through a unified gateway architecture.
Implement AI observability, token analytics, usage tracking, and cost governance.
Develop routing strategies across multiple AI models based on latency, cost, and availability.
Integrate RAG-based AI services through secure API management frameworks.
Ensure compliance with enterprise AI governance, security, and regulatory requirements.
Establish AI platform standards, reusable AI APIs, and best practices for GenAI adoption.
Support AI agent and MCP-based integrations within enterprise ecosystems.
Drive AI platform reliability, scalability, and operational excellence.
Configure, administer, and support Kong Gateway environments.
Develop and manage AI Gateway proxies for GenAI/LLM services.
Implement API security, authentication, throttling, and governance policies.
Integrate AI platforms such as Azure OpenAI and OpenAI through secure API gateways.
Deploy and manage Kong in Kubernetes-based environments.
Monitor, troubleshoot, and optimize gateway performance and availability.
Automate deployments and operational processes using DevOps tools.
Kong Gateway (OSS/Enterprise), Kong Konnect
API Management & API Lifecycle Management
AI Gateway / LLM Proxy Development
OpenAI / Azure OpenAI Integration
REST APIs, GraphQL
OAuth2, JWT, OIDC, API Security
Kubernetes, Docker, Helm
CI/CD (Jenkins, GitHub Actions, Azure DevOps)
Monitoring: Prometheus, Grafana, ELK/Splunk
Cloud Platforms: Azure, AWS, or Google Cloud Platform
Kong AI Gateway Configuration & Administration
LLM Traffic Routing, Load Balancing and Failover Management
Prompt Management, Prompt Security and Guardrails
AI Security, Responsible AI and Model Governance
Token Usage Monitoring, Rate Limiting and Cost Optimization
Multi-LLM Integration (OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini, Mistral, Llama)
Retrieval-Augmented Generation (RAG) Architecture Concepts
Vector Databases:
LLMOps, AI Observability and Model Performance Monitoring
AI API Governance, Compliance and Data Protection
Prompt Caching, Semantic Caching and Response Optimization
Model Gateway Policy Development and AI Consumption Controls
MCP (Model Context Protocol) and AI Agent Integration Concepts
GenAI Platform Engineering and Enterprise AI Enablement
Key Responsibilities:
Design and implement enterprise-grade AI Gateway solutions using Kong AI Gateway.
Configure AI-specific policies including prompt logging, content filtering, token controls, and guardrails.
Enable secure access to multiple LLM providers through a unified gateway architecture.
Implement AI observability, token analytics, usage tracking, and cost governance.
Develop routing strategies across multiple AI models based on latency, cost, and availability.
Integrate RAG-based AI services through secure API management frameworks.
Ensure compliance with enterprise AI governance, security, and regulatory requirements.
Establish AI platform standards, reusable AI APIs, and best practices for GenAI adoption.
Support AI agent and MCP-based integrations within enterprise ecosystems.
Drive AI platform reliability, scalability, and operational excellence.
Configure, administer, and support Kong Gateway environments.
Develop and manage AI Gateway proxies for GenAI/LLM services.
Implement API security, authentication, throttling, and governance policies.
Integrate AI platforms such as Azure OpenAI and OpenAI through secure API gateways.
Deploy and manage Kong in Kubernetes-based environments.
Monitor, troubleshoot, and optimize gateway performance and availability.
Automate deployments and operational processes using DevOps tools.
Similar jobs
- BE
AWS Devops/Platform Engineer
NewBESTPEGASUS LLC
VA🇺🇸Hybrid21 hours agoDockerAWSSplunk+7Technology - ZG
DevOps Engineer
NewZapcom Group
Austin, TX🇺🇸Hybrid21 hours agoAWSSonarQubeAngular+4Technology - HU
:Sr.Devops Engineer with Java (Westlake Village CA(Inperson Interview is Mandatory)
NewHUMAC INC.
Westlake Village, CA🇺🇸Hybrid21 hours agoRubyAWSJava+2Technology - SC
DevOps engineer
NewSN Cloud Solutions
Columbus, OH🇺🇸Hybrid21 hours agoDockerMicroservicesShell+27Technology - WT
Senior Site Reliability Engineer – AI/Automation
NewWebilent Technology, Inc.
Phoenix, AZ🇺🇸Hybrid21 hours agoDockerMicroservicesAWS+13Technology - AS
Power Platform Developer with DevOps, Dataverse (In Person Interview & Need 12+ years exp. candidates)
NewAnalytics Solutions
Bland, VA🇺🇸On-site21 hours agoAgileAzureC#+4Technology - SN
Infrastructure Platform Engineer(IAAS)
NewSnapCode Inc
United States🇺🇸Hybrid21 hours agoTechnology - ST
Remote Senior Databricks Platform Engineer-W2
NewSR Talent Solution Inc
United States🇺🇸Remote21 hours agoSQLAWSETL+7Technology - NI
C++ Engineer with SRE
NewNityo Infotech Corporation
San Jose, CA🇺🇸Hybrid21 hours agoMicroservicesSQLLoad Balancing+9Technology - KT
Director of DevOps
NewKforce Technology Staffing
Mesa, AZ🇺🇸Hybrid21 hours agoDockerSpinnakerAWS+16Technology - TS
Project Manager with Salesforce & Azure DevOps
NewTECHAGI SOLUTIONS LLC
Minneapolis, MN🇺🇸$60/hrHybrid21 hours agoScrumAgileAzure+1Technology - GL
DevOps/System Engineer - San Jose, CA - W2 - 3Months of Contract
NewGeopaq Logic
San Jose, CA🇺🇸Hybrid21 hours agoShellGitHTTP+2Technology