Senior DevOps Engineer

About the Role

We are building a rapidly scaling GenAI-powered SaaS platform that enables investigators to interact with complex case data through a conversational AI interface. Our system leverages RAG architecture and agentic GenAI workflows to deliver advanced AI capabilities in production.

We are looking for a Senior DevOps / Cloud Engineer to own our application services, cloud infrastructure, deployment pipelines, and production reliability in this dynamic AI environment.

This is a hands-on role focused on serverless architecture, LLM-based systems, and agentic workflows, working closely with Engineering and Customer Success to ensure the platform is reliable, scalable, and cost-efficient.

Key Responsibilities

• Own and manage application services running on GCP infrastructure, including serverless and managed services
• Design and maintain robust CI/CD pipelines for rapid, safe deployments
• Operate and optimize GenAI/LLM workloads in production, including RAG pipelines and agentic workflows
• Monitor and improve latency, cost, and reliability of AI-driven systems
• Troubleshoot complex production issues across application, data, and infrastructure layers
• Work with and optimize BigQuery-based data workflows, queries, and performance
• Support and debug multi-step AI pipelines and agent orchestration flows
• Implement and maintain observability (logging, metrics, tracing, alerting), including for AI pipelines
• Collaborate with engineering teams on architecture improvements for evolving GenAI systems
• Partner with Customer Success to investigate and resolve customer-impacting issues (minimal direct customer interaction)
• Enforce security and best practices in a sensitive data environment

What Were Looking For

• A senior engineer who can own production systems end-to-end
• Strong problem-solver with the ability to debug complex, non-deterministic AI systems
• Comfortable working in a rapidly evolving GenAI and agentic architecture
• Pragmatic mindset balancing performance, cost, and reliability
• High ownership and ability to work independently

Why Join Us

• Build and scale a real-world GenAI product with meaningful impact
• Work on cutting-edge challenges involving LLMs, RAG, and agentic systems
• Be part of a small, fast-moving, high-impact innovation team

Office Location:

Remote

Qualifications:

• 5+ years of experience in DevOps / SRE / Cloud Engineering
• Strong hands-on experience with Google Cloud Platform (GCP)
• Proven experience with serverless architectures (Cloud Run, Cloud Functions, or similar)
• Experience working with BigQuery (querying, performance tuning, troubleshooting)
• Experience running and supporting production SaaS applications
• Hands-on experience with GenAI / LLM-based applications in production
• (including RAG systems, model APIs, or similar)
• Experience supporting or operating multi-step AI pipelines or agentic workflows
• Strong experience with CI/CD pipelines (GitHub Actions, etc.)
• Solid scripting/programming skills (Python, TypeScript, Bash, or similar)
• Experience with observability and monitoring tools

Preferred Qualifications

• Experience optimizing LLM performance, cost, and reliability at scale
• Familiarity with vector databases, embeddings, and retrieval systems
• Experience with infrastructure as code (Terraform or similar)
• Background in secure or regulated environments
• Experience in fast-scaling or experimental product environments