DevOps Engineer

About the Role

Aviary is growing fast, and our infrastructure needs to grow with it. We're looking for a DevOps / Infrastructure Architect to be the first dedicated infrastructure hire on our engineering team - reporting directly to our CDO and working closely with engineering and customer success to scale our platform responsibly.

This is a high-ownership, high-visibility role for someone who wants to shape infrastructure from the ground up at a fast-moving AI company.

What You'll Own

Infrastructure Management

• Architect and manage scalable, highly available infrastructure on AWS (primary), with presence across GCP and Azure

• Introduce database redundancy and multi-region hosting to improve reliability and minimize latency for customers

• Own cost optimization without sacrificing the resilience the platform needs at scale

Deployment Pipelines

• Build and maintain CI/CD pipelines using GitHub Actions

• Manage containerized workloads with Kubernetes and Docker

• Establish deployment standards and best practices across the engineering team

Customer Onboarding

• Support technical onboarding for enterprise customers - including SAML, OIDC, and SFTP configuration

• Ensure infrastructure meets compliance and security requirements as we bring on larger clients

• Partner with the Customer Success team to reduce onboarding friction and time-to-value

AI/ML Model Infrastructure

• Own compute infrastructure for increasing model load - including self-hosted models (e.g., Deepgram) and custom model deployments

• Enable the AI/ML team to deploy, scale, and optimize models efficiently

• Build the infrastructure foundation for continued AI investment

What We're Looking For

• 4+ years of experience in a DevOps, SRE, or infrastructure engineering role

• Deep hands-on expertise with AWS; limited working knowledge of GCP and/or Azure

• Strong proficiency with infrastructure-as-code (Terraform, CloudFormation, or similar)

• Experience with Kubernetes, Docker, and GitHub Actions

• Familiarity with enterprise authentication protocols - SAML, OIDC, and secure file transfer (SFTP)

• Solid understanding of networking fundamentals (DNS, load balancing, VPCs, firewalls)

• Experience supporting AI/ML workloads or model serving infrastructure is a strong plus

• Proven ability to operate as a senior IC - owning systems end-to-end with minimal oversight

• Strong communication skills; comfortable working cross-functionally with engineering, CS, and leadership

Nice to Have

• Experience with self-hosted model infrastructure (Whisper or similar)

• Security or compliance experience (SOC 2, ISO 27001, HIPAA)

• Background in early-stage or high-growth Saas environments

What We Offer

• Equity

• Hybrid work - 3+ days in our NYC office

• Health, dental, and vision coverage

• Unlimited PTO

• In-office meals stipend

• Learning & development budget