MixMode

DevOps Engineer

• Own the reliability, performance, and operational health of production AI systems, focusing on improving complex, existing services.
• Lead efforts to refactor and harden the AI codebase to improve observability, maintainability, and resilience.
• Diagnose and resolve issues across distributed systems, including latency, throughput, data pipelines, and resource utilization.
• Design and build monitoring, alerting, and debugging tools for high-availability services.
• Partner with researchers and ML engineers to productionize models at scale.
• Establish best practices for testing, deployment, capacity planning, and incident response.
• Serve as a technical leader during on-call rotations, driving incident response, postmortems, and continuous system improvements.

Senior Software Reliability Engineer – AI