As our DevOps SRE, you’ll help us build and operate the infrastructure needed to scale autonomous cybersecurity investigations powered by LLMs.

• Deploy and Optimize Our LLM Infrastructure
  Design and run scalable inference environments, optimize performance (latency, throughput, cost), and set up monitoring and logging for everything.

• Enable Multi-Tenant Client Deployments
  Architect and implement infrastructure that can support secure, isolated deployments across on-prem, hybrid, and cloud setups.

• Automate CI/CD and Infrastructure as Code (IaC)
  Build bulletproof pipelines, reduce manual work, and implement best-in-class IaC using Terraform or similar tools.

You’re probably a great fit if you have:

• Solid experience with cloud infrastructure (ideally GCP)

• Experience with on-premise, private cloud and multi-tenant cloud deployment

• Proficiency in Infrastructure as Code (e.g., Terraform)

• Understanding of networking, IAM, and security best practices

• Experience building robust observability stacks (monitoring, alerting, logging)

• Familiarity with multi-tenant security and network isolation

• Strong communication and problem-solving mindset

• Bonus if you have experience deploying and optimizing LLMs in production

What success looks like

• LLMs deployed at scale with optimal throughput, latency, and cost-efficiency

• On-prem & multi-tenant deployments running smoothly and securely

• Automated infrastructure that’s stable, fast to iterate upon and can be reproduced easily

• A better developer experience and stronger CI/CD reliability across the team

Our stack

• Github CI/CD

• Infrastructure: Kubernetes on Google Cloud Provider

• Database: Postgresql

  • 5 services (in Python / Typescript)

  • Deployed via Helm Charts

Why join Qevlar AI?

• Work on cutting-edge AI infrastructure challenges with a real-world impact

• Contribute to building a secure, AI-native platform changing how cybersecurity is done

• Be part of a tight-knit, high-caliber team that values autonomy and speed

• Opportunity for equity and early-stage ownership

• Remote-friendly, flexible work culture

1. Introduction Call

2. Technical Interview with our Head of Engineering deep dive into cloud architecture, IaC, and infrastructure troubleshooting.

3. Case Study / Infrastructure Design

4. Meet the Team

This is a high-impact role for someone who wants to architect modern AI infra — and be a key pillar in how we scale. Ready to dive in?