Senior Software Engineer (MLOps) – Serving

Architect and build scalable ML/LLM model-serving systems across data centers with strong SLAs, observability, and reliability.
Design and optimize Ray-based inference infrastructure to handle both low- and high-throughput workloads.
Enable applied scientists to deploy and test models via self-service tools, CI/CD pipelines, and rollback mechanisms.
Implement A/B testing and shadow deployment capabilities to evaluate new model versions in production.
Collaborate with platform teams to improve GPU provisioning, traffic routing, and runtime performance.
Instrument inference workflows with telemetry (latency, token counts, errors) to drive performance and safety analysis.