Senior Machine Learning Engineer, Services/MLOps

What you'll do

• Manage the full serving lifecycle for heterogeneous model pipelines including packaging, versioned rollout, and autoscaling.
• Deploy and scale multi-model pipelines to meet enterprise requirements for latency and throughput.
• Ensure served model quality matches training environments by closing gaps in precision and preprocessing.
• Engineer enterprise-grade features such as multi-tenant boundaries and data isolation for customer IP protection.
• Build infrastructure for rapid pipeline deployment, including monitoring, alerting, and observability systems.
• Establish automated quality gates to detect regressions and drift before models reach production.
• Optimize GPU capacity and costs through efficient batching and right-sizing of acceleration fleets.
• Perform operational ML tasks including on-call rotations, incident response, and postmortems for service availability.

What we're looking for

• Must have 5+ years of experience in machine learning engineering with ownership of production ML or inference services at scale.
• Requires strong Python and deep-learning engineering skills using PyTorch.
• Must have experience deploying and scaling model-backed services, including multi-model pipelines behind APIs.
• Requires expertise in building observability, monitoring, and alerting for production services to meet latency and throughput targets.
• Must be comfortable working across various generative architectures including LLMs, VLMs, diffusion models, and 3D/mesh models.
• Requires experience with multi-tenant systems and data isolation in enterprise or regulated contexts.
• Must be fluent in containers and orchestration (Docker, Kubernetes), CI/CD for ML, and major cloud platforms like AWS or Azure.
• Requires a Master’s or PhD in Computer Science, Computer Engineering, or a related field, or equivalent practical experience.