Senior DevOps Engineer

You will be joining the AI Platform team responsible for building and maintaining the cloud infrastructure, large language model (LLM) gateway, and serving layer that support our wealth management product. This role requires hands-on ownership of Azure-based infrastructure, taking projects from code to production while ensuring reliability and cost efficiency.

Key Responsibilities
- Develop, deploy, and operate cloud infrastructure primarily on Azure, ensuring systems run smoothly and cost-effectively.
- Manage and maintain the LLM gateway and serving layers that power AI-driven features in the product.
- Implement infrastructure as code using tools like Terraform or Bicep, managing modules and state with discipline.
- Troubleshoot and debug production issues using logs, traces, and reproducible steps to identify root causes.
- Collaborate with cross-functional teams to optimize cloud resources and improve system performance.
- Utilize modern AI-assisted development tools to enhance productivity and code quality.

Required Qualifications
- 3 to 5 years of experience in platform, backend, or infrastructure engineering with direct ownership of production systems.
- Hands-on experience with major cloud providers such as Azure, AWS, or GCP, including strong knowledge of compute resources, private networking, containerization, and serverless architectures.
- Proficiency in infrastructure as code practices using Terraform, Bicep, or similar tools.
- Strong debugging skills, relying on data-driven investigation rather than guesswork.
- Working understanding of large language models, including concepts like tokens, context windows, and quota management.
- Familiarity with AI-assisted development environments such as Claude Code, Cursor, Antigravity, or OpenCode.

Preferred Qualifications and Benefits
- Direct experience with Azure services including VNets, subnets, private endpoints, Container Apps, and Function Apps.
- Background in system design and familiarity with AI infrastructure terminology such as tokenization, requests per minute, and token budgeting.
- Advanced Python skills, especially with asynchronous programming (asyncio), concurrency, and threading concepts.
- Experience building or operating LLM gateways or similar proxy/routing layers.
- Knowledge of open-source model deployment and serving platforms like vLLM, Ollama, or Text Generation Inference (TGI), including infrastructure optimization.
- Exposure to LLM safety and governance practices such as PII redaction, data classification, and prompt/response guardrails.
- Expertise in cloud cost optimization strategies, including scaling plans and managing cold starts in serverless environments.
- Familiarity with observability tools such as Azure Application Insights, OpenTelemetry, or equivalents to monitor and analyze system health.

This role offers the opportunity to work at the intersection of cloud infrastructure and cutting-edge AI technology, contributing to a product that transforms wealth management through intelligent automation and scalable solutions.