AI Platform Engineering Specialist

Key Responsibilities
Design, build, deploy, and operate AI Gateway solutions across Azure and AWS, taking solutions from proof of concept through production
Develop and enhance Python services using FastAPI and Flask for inference, onboarding, and administrative APIs
Integrate new model providers and model families, including Azure AI Foundry, Azure OpenAI, and AWS Bedrock
Implement request signing, streaming responses, failover, and quota-handling capabilities
Implement secure cloud-native authentication and secrets management using Entra ID, Managed Identity, workload federation, AWS IAM roles, and STS
Build and maintain entitlement and authorization data layers using SQL Server and PostgreSQL, including schema changes, migrations, and data-quality controls
Develop platform governance capabilities, including rate limiting, token accounting, content guardrails, audit logging, and chargeback reporting
Deploy and operate services across Kubernetes environments, including on-premises, AKS, and EKS, using Helm, GitOps, and Terraform
Maintain and enhance CI/CD pipelines using Jenkins and GitHub Actions
Build comprehensive monitoring and observability capabilities using Prometheus, Grafana, Loki, and Snowflake
Partner with cloud, network, and security teams on connectivity, egress policies, network controls, architecture reviews, and supporting documentation
Participate in on-call production support, investigate incidents, and implement fixes and platform hardening improvements
Develop tests and technical documentation as part of the delivery process
Review peer code and contribute to overall engineering quality and best practices
Required Qualifications
5+ years of experience
Bachelor's Degree
English
Skills
Python Development
Kubernetes
Microsoft Azure
AWS
API Gateway Development
Authentication and Authorization
Infrastructure as Code
CI/CD Pipelines
SQL and Relational Data Modeling
Monitoring and Observability
Generative AI and LLM Platform Engineering
Data Pipelines
Redis and Distributed Rate Limiting
Production Support and On-Call Incident Response
Technical Documentation
Code Review Facilitation
Written and Verbal Communication
Cross-functional Collaboration
Software Testing Practices
Regulated Enterprise Environment Delivery
Architecture Reviews
Schedule
Start date: 2026-10-12